Security Now (Audio) TWiT https://twit.tv/shows/security-now TWiT Feed Generator v4.11.3 http://blogs.law.harvard.edu/tech/rss en-US This work is licensed under a Creative Commons License - Attribution-NonCommercial-NoDerivatives 4.0 International - http://creativecommons.org/licenses/by-nc-nd/4.0/ http://creativecommons.org/licenses/by-nc-nd/4.0/ feedmail@twit.tv (TWiT Editors) feedmail@twit.tv (TWiT Engineering) 720 weekly 1 Tue, 08 Sep 2026 19:35:03 PDT Tue, 08 Sep 2026 19:35:03 PDT weekly Petaluma, CA episodic Steve Gibson explains cybersecurity threats, hacks, vulnerabilities, and defense. Cybersecurity guru Steve Gibson joins Leo Laporte every Tuesday. Steve and Leo break down the latest cybercrime and hacking stories, offering a deep understanding of what's happening and how to protect yourself and your business. Security Now is a must listen for security professionals every week.

You can join Club TWiT for $10 per month and get ad-free audio and video feeds for all our shows plus everything else the club offers...or get just this podcast ad-free for $5 per month.

New episodes every Tuesday.

]]> Cybersecurity guru Steve Gibson joins Leo Laporte every Tuesday. Steve and Leo break down the latest cybercrime and hacking stories, offering a deep understanding of what's happening and how to protect yourself and your business. Security Now is a must listen for security professionals every week.

You can join Club TWiT for $10 per month and get ad-free audio and video feeds for all our shows plus everything else the club offers...or get just this podcast ad-free for $5 per month.

New episodes every Tuesday.

]]> TWiT, Technology, Steve Gibson, Leo Laporte, security, spyware, malware, hacking, cyber crime, encryption tv-g no no No Become a Club TWiT member! Leo Laporte feedmail@twit.tv Technology Security Security Now (Audio) https://elroy.twit.tv/sites/default/files/styles/twit_album_art_2048x2048/public/images/shows/security_now/album_art/audio/sn2022_albumart_standard_2400.jpg https://twit.tv/shows/security-now https://feeds.twit.tv/sn.xml SN 1095: AI-Driven Expertise Loss - Gemini, Hugging Face, and the AI Arms Race AI-Driven Expertise Loss - Gemini, Hugging Face, and the AI Arms Race full TWiT Tue, 08 Sep 2026 19:14:17 PDT 1095 1095 https://twit.tv/shows/security-now/episodes/1095 https://twit.tv/shows/security-now/episodes/1095 Help & How To Technology Security no Gemini, Hugging Face, and the AI Arms Race AI-driven expertise loss, Microsoft Patch Tuesday, Windows security updates, memory integrity, hypervisor-protected code integrity, Firefox smart window, CISA cybersecurity services, OpenAI GPT-6 Astra, NVIDIA Hugging Face acquisition OpenAI's latest advances have the rumor mill buzzing about "hidden thoughts" and unsupervisable models, but are AI safety experts panicking over the wrong threat? Get the clear-headed take behind the headlines.

  • We start out with a classic old school hack against Dropbox.
  • Next Patch Tuesday will be enabling "Memory Integrity" for many.
  • Firefox moved to 155 and obtained a dumb Smart Window.
  • CISA is terminating 6 most valuable cybersecurity services.
  • OpenAI advanced to topof the heap with GPT-6 Astra.
  • But... is it now hiding some of its thinking from monitoring?
  • Nvidia is acquiring Hugging Face. Who's that good for?
  • Google releases Gemini 3.8 Flash and Cyber. Is it good?
  • Chinese cyberespionage is using AI to become more slippery.
  • Matthew Green proposes a fascinating take on AI bug drought.
  • A lifelong safety engineer contemplates AI-driven loss of expertise.

Show Notes - https://www.grc.com/sn/SN-1095-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> OpenAI's latest advances have the rumor mill buzzing about "hidden thoughts" and unsupervisable models, but are AI safety experts panicking over the wrong threat? Get the clear-headed take behind the headlines.

  • We start out with a classic old school hack against Dropbox.
  • Next Patch Tuesday will be enabling "Memory Integrity" for many.
  • Firefox moved to 155 and obtained a dumb Smart Window.
  • CISA is terminating 6 most valuable cybersecurity services.
  • OpenAI advanced to topof the heap with GPT-6 Astra.
  • But... is it now hiding some of its thinking from monitoring?
  • Nvidia is acquiring Hugging Face. Who's that good for?
  • Google releases Gemini 3.8 Flash and Cyber. Is it good?
  • Chinese cyberespionage is using AI to become more slippery.
  • Matthew Green proposes a fascinating take on AI bug drought.
  • A lifelong safety engineer contemplates AI-driven loss of expertise.

Show Notes - https://www.grc.com/sn/SN-1095-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> OpenAI's latest advances have the rumor mill buzzing about "hidden thoughts" and unsupervisable models, but are AI safety experts panicking over the wrong threat? Get the clear-headed take behind the headlines.

  • We start out with a classic old school hack against Dropbox.
  • Next Patch Tuesday will be enabling "Memory Integrity" for many.
  • Firefox moved to 155 and obtained a dumb Smart Window.
  • CISA is terminating 6 most valuable cybersecurity services.
  • OpenAI advanced to topof the heap with GPT-6 Astra.
  • But... is it now hiding some of its thinking from monitoring?
  • Nvidia is acquiring Hugging Face. Who's that good for?
  • Google releases Gemini 3.8 Flash and Cyber. Is it good?
  • Chinese cyberespionage is using AI to become more slippery.
  • Matthew Green proposes a fascinating take on AI bug drought.
  • A lifelong safety engineer contemplates AI-driven loss of expertise.

Show Notes - https://www.grc.com/sn/SN-1095-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> https://pdst.fm/e/pscrb.fm/rss/p/mgln.ai/e/294/cdn.twit.tv/megaphone/sn_1095/ARML6344215591.mp3 3:06:06 SN 1095: AI-Driven Expertise Loss - Gemini, Hugging Face, and the AI Arms Race Gemini, Hugging Face, and the AI Arms Race AI-driven expertise loss, Microsoft Patch Tuesday, Windows security updates, memory integrity, hypervisor-protected code integrity, Firefox smart window, CISA cybersecurity services, OpenAI GPT-6 Astra, NVIDIA Hugging Face acquisition nonadult tv-g IAB19 Steve Gibson Leo Laporte Steve Gibson Leo Laporte SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code? AI Patching Shortcomings - Should You Trust AI-Generated Code? full TWiT Tue, 01 Sep 2026 19:10:31 PDT 1094 1094 https://twit.tv/shows/security-now/episodes/1094 https://twit.tv/shows/security-now/episodes/1094 Help & How To Technology Security no Should You Trust AI-Generated Code? AI patching shortcomings, prompt injection abuse, security flaws in AI code, vulnerability remediation, large language models, LLM security, architectural instruction data separation, neural network limitations, role confusion problem AI-generated code is flooding the industry, but researchers reveal that almost half of it contains critical vulnerabilities. This week, we unpack what happens when the race for automation outpaces security best practices.

  • A possible means for preventing prompt injection abuse.
  • Clear evidence of Chinese-made router malicious intent.
  • A cool before and after SpinRite graph of SSD performance.
  • How about adding unpredictable hashes to role tags?
  • What did Claude make of last week's podcast?
  • Could much better harnesses prevent prompt injection?
  • A listener wants us to stop saying AI "thinks".
  • AI designers ignore well-understood security concepts.
  • Can we explain LLM AI using conventional computer terms?
  • A listener strongly dislikes the term "rotating credentials".
  • The land of AI is being filled with "meat proxies".
  • Researchers exhaustively test frontier model vulnerability remediation. (hint: It does not go well.)

Show Notes - https://www.grc.com/sn/SN-1094-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> AI-generated code is flooding the industry, but researchers reveal that almost half of it contains critical vulnerabilities. This week, we unpack what happens when the race for automation outpaces security best practices.

  • A possible means for preventing prompt injection abuse.
  • Clear evidence of Chinese-made router malicious intent.
  • A cool before and after SpinRite graph of SSD performance.
  • How about adding unpredictable hashes to role tags?
  • What did Claude make of last week's podcast?
  • Could much better harnesses prevent prompt injection?
  • A listener wants us to stop saying AI "thinks".
  • AI designers ignore well-understood security concepts.
  • Can we explain LLM AI using conventional computer terms?
  • A listener strongly dislikes the term "rotating credentials".
  • The land of AI is being filled with "meat proxies".
  • Researchers exhaustively test frontier model vulnerability remediation. (hint: It does not go well.)

Show Notes - https://www.grc.com/sn/SN-1094-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> AI-generated code is flooding the industry, but researchers reveal that almost half of it contains critical vulnerabilities. This week, we unpack what happens when the race for automation outpaces security best practices.

  • A possible means for preventing prompt injection abuse.
  • Clear evidence of Chinese-made router malicious intent.
  • A cool before and after SpinRite graph of SSD performance.
  • How about adding unpredictable hashes to role tags?
  • What did Claude make of last week's podcast?
  • Could much better harnesses prevent prompt injection?
  • A listener wants us to stop saying AI "thinks".
  • AI designers ignore well-understood security concepts.
  • Can we explain LLM AI using conventional computer terms?
  • A listener strongly dislikes the term "rotating credentials".
  • The land of AI is being filled with "meat proxies".
  • Researchers exhaustively test frontier model vulnerability remediation. (hint: It does not go well.)

Show Notes - https://www.grc.com/sn/SN-1094-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> https://pdst.fm/e/pscrb.fm/rss/p/mgln.ai/e/294/cdn.twit.tv/megaphone/sn_1094/ARML1112174439.mp3 2:51:59 SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code? Should You Trust AI-Generated Code? AI patching shortcomings, prompt injection abuse, security flaws in AI code, vulnerability remediation, large language models, LLM security, architectural instruction data separation, neural network limitations, role confusion problem nonadult tv-g IAB19 Steve Gibson Leo Laporte Steve Gibson Leo Laporte SN 1093: Tokens in the Stream - Why LLMs are inherently insecure and prompt injection will persist Tokens in the Stream - Why LLMs are inherently insecure and prompt injection will persist full TWiT Tue, 25 Aug 2026 19:57:43 PDT 1093 1093 https://twit.tv/shows/security-now/episodes/1093 https://twit.tv/shows/security-now/episodes/1093 Help & How To Technology Security no Why LLMs are inherently insecure and prompt injection will persist AI security, prompt injection, role confusion, large language models, LLM vulnerabilities, neural networks, AI distillation, model training, Anthropic Claude Mythos 5, Bitwarden Secrets Manager, open-source security, system prompt tags Turns out, every chatbot conversation runs on a messy hack at the heart of language models, making prompt injection an unsolved—and possibly unsolvable—security threat. Steve and Leo unravel the research that explains why "roles" in AI aren't what you think they are.

  • Understanding the controversy surrounding "AI Model Distillation"
  • Anthropic moves to make their most powerful Mythos 5 model more widely available.
  • Bitwarden's "Secrets Manager" offering prevents agentic and prompt injection abuse.
  • The astounding and disturbing truth about the way conversation AI actually works

Show Notes - https://www.grc.com/sn/SN-1093-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> Turns out, every chatbot conversation runs on a messy hack at the heart of language models, making prompt injection an unsolved—and possibly unsolvable—security threat. Steve and Leo unravel the research that explains why "roles" in AI aren't what you think they are.

  • Understanding the controversy surrounding "AI Model Distillation"
  • Anthropic moves to make their most powerful Mythos 5 model more widely available.
  • Bitwarden's "Secrets Manager" offering prevents agentic and prompt injection abuse.
  • The astounding and disturbing truth about the way conversation AI actually works

Show Notes - https://www.grc.com/sn/SN-1093-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> Turns out, every chatbot conversation runs on a messy hack at the heart of language models, making prompt injection an unsolved—and possibly unsolvable—security threat. Steve and Leo unravel the research that explains why "roles" in AI aren't what you think they are.

  • Understanding the controversy surrounding "AI Model Distillation"
  • Anthropic moves to make their most powerful Mythos 5 model more widely available.
  • Bitwarden's "Secrets Manager" offering prevents agentic and prompt injection abuse.
  • The astounding and disturbing truth about the way conversation AI actually works

Show Notes - https://www.grc.com/sn/SN-1093-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> https://pdst.fm/e/pscrb.fm/rss/p/mgln.ai/e/294/cdn.twit.tv/megaphone/sn_1093/ARML1998265017.mp3 2:48:10 SN 1093: Tokens in the Stream - Why LLMs are inherently insecure and prompt injection will persist Why LLMs are inherently insecure and prompt injection will persist AI security, prompt injection, role confusion, large language models, LLM vulnerabilities, neural networks, AI distillation, model training, Anthropic Claude Mythos 5, Bitwarden Secrets Manager, open-source security, system prompt tags nonadult tv-g IAB19 Steve Gibson Leo Laporte Steve Gibson Leo Laporte SN 1092: Restraint Abliteration - Rotating Keys, Broken Guardrails Restraint Abliteration - Rotating Keys, Broken Guardrails full TWiT Tue, 18 Aug 2026 19:40:54 PDT 1092 1092 https://twit.tv/shows/security-now/episodes/1092 https://twit.tv/shows/security-now/episodes/1092 Help & How To Technology Security no Rotating Keys, Broken Guardrails AI security, supply chain attack, LightLLM, Trivy vulnerability scanner, credential leaks, open-source AI proxy, dual-use knowledge, refusal behavior, model obliteration, credential rotation, RLHF, Direct Preference Optimization, DPO, Anthropic, openAI From autocorrect to full-fledged conversationalists, discover how a few tweaks transformed language models—and why understanding this shift exposes urgent questions about AI safety and control.

  • Trusting an open source AI proxy might bite you.
  • France's under-15 social media ban hits its constitution.
  • A bit of AI prompting found a serious bug in Zoom.
  • AI-based network defenders see a stock price jump.
  • A (very) deep dive into the operation of AI chatbots

Show Notes - https://www.grc.com/sn/SN-1092-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> From autocorrect to full-fledged conversationalists, discover how a few tweaks transformed language models—and why understanding this shift exposes urgent questions about AI safety and control.

  • Trusting an open source AI proxy might bite you.
  • France's under-15 social media ban hits its constitution.
  • A bit of AI prompting found a serious bug in Zoom.
  • AI-based network defenders see a stock price jump.
  • A (very) deep dive into the operation of AI chatbots

Show Notes - https://www.grc.com/sn/SN-1092-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> From autocorrect to full-fledged conversationalists, discover how a few tweaks transformed language models—and why understanding this shift exposes urgent questions about AI safety and control.

  • Trusting an open source AI proxy might bite you.
  • France's under-15 social media ban hits its constitution.
  • A bit of AI prompting found a serious bug in Zoom.
  • AI-based network defenders see a stock price jump.
  • A (very) deep dive into the operation of AI chatbots

Show Notes - https://www.grc.com/sn/SN-1092-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> https://pdst.fm/e/pscrb.fm/rss/p/mgln.ai/e/294/cdn.twit.tv/megaphone/sn_1092/ARML9872780120.mp3 2:49:05 SN 1092: Restraint Abliteration - Rotating Keys, Broken Guardrails Rotating Keys, Broken Guardrails AI security, supply chain attack, LightLLM, Trivy vulnerability scanner, credential leaks, open-source AI proxy, dual-use knowledge, refusal behavior, model obliteration, credential rotation, RLHF, Direct Preference Optimization, DPO, Anthropic, openAI nonadult tv-g IAB19 Steve Gibson Leo Laporte Steve Gibson Leo Laporte SN 1091: The Post BlackHat State of AI - When AI Writes Malware The Post BlackHat State of AI - When AI Writes Malware full TWiT Tue, 11 Aug 2026 19:36:32 PDT 1091 1091 https://twit.tv/shows/security-now/episodes/1091 https://twit.tv/shows/security-now/episodes/1091 Help & How To Technology Security no When AI Writes Malware AI security, Anthropic, Meta, OpenAI breakout, Hugging Face hack, chrome vulnerabilities, pfsense, NF Sensei, bruce schneier, AI genies, cybersecurity, agentic ai, prompt injection, Simon Willison, AI bug bounty, Apple bug reports, Mythos model AI agents are breaking free from their test environments, outsmarting their creators and breaching real-world networks in ways that no one predicted. Discover how these agentic models are changing the game for both cyber offense and defense.

  • Anthropic's agentic AI also broke free and hacked others.
  • We know much (much!) more about the OpenAI breakout.
  • OpenAI posts that they're pausing "Astra" - even internally.
  • What was that about AI recently cracking (or denting) cryptography.
  • Bruce Schneier brilliantly equates AI agents to capricious genies.
  • Apple doesn't react so well to the new deluge of security reports.
  • Chrome 149 + 150 updates together fix 1,072 bugs. Yikes.
  • psSense's creator is working to finish its nfSensei, its successor

Show Notes - https://www.grc.com/sn/SN-1091-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> AI agents are breaking free from their test environments, outsmarting their creators and breaching real-world networks in ways that no one predicted. Discover how these agentic models are changing the game for both cyber offense and defense.

  • Anthropic's agentic AI also broke free and hacked others.
  • We know much (much!) more about the OpenAI breakout.
  • OpenAI posts that they're pausing "Astra" - even internally.
  • What was that about AI recently cracking (or denting) cryptography.
  • Bruce Schneier brilliantly equates AI agents to capricious genies.
  • Apple doesn't react so well to the new deluge of security reports.
  • Chrome 149 + 150 updates together fix 1,072 bugs. Yikes.
  • psSense's creator is working to finish its nfSensei, its successor

Show Notes - https://www.grc.com/sn/SN-1091-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> AI agents are breaking free from their test environments, outsmarting their creators and breaching real-world networks in ways that no one predicted. Discover how these agentic models are changing the game for both cyber offense and defense.

  • Anthropic's agentic AI also broke free and hacked others.
  • We know much (much!) more about the OpenAI breakout.
  • OpenAI posts that they're pausing "Astra" - even internally.
  • What was that about AI recently cracking (or denting) cryptography.
  • Bruce Schneier brilliantly equates AI agents to capricious genies.
  • Apple doesn't react so well to the new deluge of security reports.
  • Chrome 149 + 150 updates together fix 1,072 bugs. Yikes.
  • psSense's creator is working to finish its nfSensei, its successor

Show Notes - https://www.grc.com/sn/SN-1091-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> https://pdst.fm/e/pscrb.fm/rss/p/mgln.ai/e/294/cdn.twit.tv/megaphone/sn_1091/ARML1975583473.mp3 2:51:12 SN 1091: The Post BlackHat State of AI - When AI Writes Malware When AI Writes Malware AI security, Anthropic, Meta, OpenAI breakout, Hugging Face hack, chrome vulnerabilities, pfsense, NF Sensei, bruce schneier, AI genies, cybersecurity, agentic ai, prompt injection, Simon Willison, AI bug bounty, Apple bug reports, Mythos model nonadult tv-g IAB19 Steve Gibson Leo Laporte Steve Gibson Leo Laporte SN 1090: Black Hat - The Hidden Flaws in AI Security Nobody Saw Coming Black Hat - The Hidden Flaws in AI Security Nobody Saw Coming full TWiT Wed, 05 Aug 2026 17:39:56 PDT 1090 1090 https://twit.tv/shows/security-now/episodes/1090 https://twit.tv/shows/security-now/episodes/1090 Help & How To Technology Security no The Hidden Flaws in AI Security Nobody Saw Coming Black Hat Conference, ai and security, ThreatLocker, def con, autonomous vehicles, Zoox hack, Claude AI, copilot, Home Assistant, local AI models, cybersecurity, open source vulnerabilities, Mythos, M-DASH, AI in cryptography, vulnerability discovery At Black Hat Las Vegas, the Security Now crew digs into how AI is not just finding hidden software bugs but also fueling both groundbreaking innovation and alarming new exploits. When open models can launch surprise Bitcoin heists, who draws the line between forbidden knowledge and genuine progress?

• Black Hat and DEF CON: Hacking Stories and Conference Culture
• Zoox Ride-Hailing Hack and Over-the-Air Vulnerabilities
• Autonomous Vehicles, AI, and the Security Implications
• Hosts Share Personal Adoption and Use of AI Tools
• AI-Powered Coding: From Hobbyists to Advanced Agency Chains
• Local Models vs. Cloud AI: Privacy, Cost, and Control
• App Development Democratized: Listeners Build Custom Solutions With AI
• Code Generation, Testing, and Managing AI-Driven Project Cycles
• AI's Role in Security: Vulnerability Discovery, Exploitation, and Patch Challenges
• Technical Debt and the Race to Patch Decades-Old Bugs
• The Dual-Use Dilemma: AI Tools for Both Attack and Defense
• Guardrails, Model Partitioning, and the Fight Over Forbidden Knowledge
• Open vs. Restricted AI: Global Models, Distillation, and Free Speech
• LLM Security Weaknesses: Prompt Injection and Role Confusion Exposed
• The Reliability Problem: Probabilistic AI and Non-Deterministic Software
• AI Progress: Public Perception, Skepticism, and "Hogwash" Rebuttals
• Reflections on AI's Fast Evolution and the Sci-Fi Reality Gap
• Closing Thoughts: Tech Community, Listener Feedback, and the Future of Security Now

Hosts: Steve Gibson, Leo Laporte, Richard Campbell, and Paul Thurrott

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> At Black Hat Las Vegas, the Security Now crew digs into how AI is not just finding hidden software bugs but also fueling both groundbreaking innovation and alarming new exploits. When open models can launch surprise Bitcoin heists, who draws the line between forbidden knowledge and genuine progress?

• Black Hat and DEF CON: Hacking Stories and Conference Culture
• Zoox Ride-Hailing Hack and Over-the-Air Vulnerabilities
• Autonomous Vehicles, AI, and the Security Implications
• Hosts Share Personal Adoption and Use of AI Tools
• AI-Powered Coding: From Hobbyists to Advanced Agency Chains
• Local Models vs. Cloud AI: Privacy, Cost, and Control
• App Development Democratized: Listeners Build Custom Solutions With AI
• Code Generation, Testing, and Managing AI-Driven Project Cycles
• AI's Role in Security: Vulnerability Discovery, Exploitation, and Patch Challenges
• Technical Debt and the Race to Patch Decades-Old Bugs
• The Dual-Use Dilemma: AI Tools for Both Attack and Defense
• Guardrails, Model Partitioning, and the Fight Over Forbidden Knowledge
• Open vs. Restricted AI: Global Models, Distillation, and Free Speech
• LLM Security Weaknesses: Prompt Injection and Role Confusion Exposed
• The Reliability Problem: Probabilistic AI and Non-Deterministic Software
• AI Progress: Public Perception, Skepticism, and "Hogwash" Rebuttals
• Reflections on AI's Fast Evolution and the Sci-Fi Reality Gap
• Closing Thoughts: Tech Community, Listener Feedback, and the Future of Security Now

Hosts: Steve Gibson, Leo Laporte, Richard Campbell, and Paul Thurrott

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> At Black Hat Las Vegas, the Security Now crew digs into how AI is not just finding hidden software bugs but also fueling both groundbreaking innovation and alarming new exploits. When open models can launch surprise Bitcoin heists, who draws the line between forbidden knowledge and genuine progress?

• Black Hat and DEF CON: Hacking Stories and Conference Culture
• Zoox Ride-Hailing Hack and Over-the-Air Vulnerabilities
• Autonomous Vehicles, AI, and the Security Implications
• Hosts Share Personal Adoption and Use of AI Tools
• AI-Powered Coding: From Hobbyists to Advanced Agency Chains
• Local Models vs. Cloud AI: Privacy, Cost, and Control
• App Development Democratized: Listeners Build Custom Solutions With AI
• Code Generation, Testing, and Managing AI-Driven Project Cycles
• AI's Role in Security: Vulnerability Discovery, Exploitation, and Patch Challenges
• Technical Debt and the Race to Patch Decades-Old Bugs
• The Dual-Use Dilemma: AI Tools for Both Attack and Defense
• Guardrails, Model Partitioning, and the Fight Over Forbidden Knowledge
• Open vs. Restricted AI: Global Models, Distillation, and Free Speech
• LLM Security Weaknesses: Prompt Injection and Role Confusion Exposed
• The Reliability Problem: Probabilistic AI and Non-Deterministic Software
• AI Progress: Public Perception, Skepticism, and "Hogwash" Rebuttals
• Reflections on AI's Fast Evolution and the Sci-Fi Reality Gap
• Closing Thoughts: Tech Community, Listener Feedback, and the Future of Security Now

Hosts: Steve Gibson, Leo Laporte, Richard Campbell, and Paul Thurrott

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> https://pdst.fm/e/pscrb.fm/rss/p/mgln.ai/e/294/cdn.twit.tv/megaphone/sn_1090/ARML8757985620.mp3 2:05:11 SN 1090: Black Hat - The Hidden Flaws in AI Security Nobody Saw Coming The Hidden Flaws in AI Security Nobody Saw Coming Black Hat Conference, ai and security, ThreatLocker, def con, autonomous vehicles, Zoox hack, Claude AI, copilot, Home Assistant, local AI models, cybersecurity, open source vulnerabilities, Mythos, M-DASH, AI in cryptography, vulnerability discovery nonadult tv-g IAB19 Steve Gibson Leo Laporte Richard Campbell Paul Thurrott Steve Gibson Leo Laporte Richard Campbell Paul Thurrott SN 1089: Models Go Rogue & ExploitGym - Regulators, Start Your Engines Models Go Rogue & ExploitGym - Regulators, Start Your Engines full TWiT Tue, 28 Jul 2026 19:13:13 PDT 1089 1089 https://twit.tv/shows/security-now/episodes/1089 https://twit.tv/shows/security-now/episodes/1089 Help & How To Technology Security no Regulators, Start Your Engines openAI, hugging face, AI alignment, AI model containment, autonomous ai agents, AI cybersecurity, ExploitGym, vulnerability exploitation, GPT-5.6 Sol, ai guardrails, cybersecurity incident, Linux kernel vulnerabilities, WordPress vulnerability What happens when an unconstrained OpenAI model goes rogue and hacks into Hugging Face, breaching real-world security boundaries? This episode unpacks a watershed moment for AI safety that has everyone in cybersecurity talking.

  • OpenAI's unconstrained internal testing AI got loose, attacked Hugging Face.
  • We hear from OpenAI, Hugging Face and Andrew Ng.
  • GRC went off the air Friday. Was GRC hacked? What happened?
  • The Linux kernel project repairs 442 CVEs in a single batch.
  • LG's PC monitors cause PC adware installation.
  • France bans all social media access below age 15.
  • WordPress' recent CRITICAL vulnerability claims victims.
  • Amazing details about "Rocky" from Andy Weir.
  • The new AI exploit ranking benchmark that caused the breakout

Show Notes - https://www.grc.com/sn/SN-1089-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> What happens when an unconstrained OpenAI model goes rogue and hacks into Hugging Face, breaching real-world security boundaries? This episode unpacks a watershed moment for AI safety that has everyone in cybersecurity talking.

  • OpenAI's unconstrained internal testing AI got loose, attacked Hugging Face.
  • We hear from OpenAI, Hugging Face and Andrew Ng.
  • GRC went off the air Friday. Was GRC hacked? What happened?
  • The Linux kernel project repairs 442 CVEs in a single batch.
  • LG's PC monitors cause PC adware installation.
  • France bans all social media access below age 15.
  • WordPress' recent CRITICAL vulnerability claims victims.
  • Amazing details about "Rocky" from Andy Weir.
  • The new AI exploit ranking benchmark that caused the breakout

Show Notes - https://www.grc.com/sn/SN-1089-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> What happens when an unconstrained OpenAI model goes rogue and hacks into Hugging Face, breaching real-world security boundaries? This episode unpacks a watershed moment for AI safety that has everyone in cybersecurity talking.

  • OpenAI's unconstrained internal testing AI got loose, attacked Hugging Face.
  • We hear from OpenAI, Hugging Face and Andrew Ng.
  • GRC went off the air Friday. Was GRC hacked? What happened?
  • The Linux kernel project repairs 442 CVEs in a single batch.
  • LG's PC monitors cause PC adware installation.
  • France bans all social media access below age 15.
  • WordPress' recent CRITICAL vulnerability claims victims.
  • Amazing details about "Rocky" from Andy Weir.
  • The new AI exploit ranking benchmark that caused the breakout

Show Notes - https://www.grc.com/sn/SN-1089-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> https://pdst.fm/e/pscrb.fm/rss/p/mgln.ai/e/294/cdn.twit.tv/megaphone/sn_1089/ARML4918737805.mp3 3:07:56 SN 1089: Models Go Rogue & ExploitGym - Regulators, Start Your Engines Regulators, Start Your Engines openAI, hugging face, AI alignment, AI model containment, autonomous ai agents, AI cybersecurity, ExploitGym, vulnerability exploitation, GPT-5.6 Sol, ai guardrails, cybersecurity incident, Linux kernel vulnerabilities, WordPress vulnerability nonadult tv-g IAB19 Steve Gibson Leo Laporte Steve Gibson Leo Laporte SN 1088: A Nefarious Novel Use for AI - Ransomware Negotiations Go High-Tech A Nefarious Novel Use for AI - Ransomware Negotiations Go High-Tech full TWiT Tue, 21 Jul 2026 19:39:17 PDT 1088 1088 https://twit.tv/shows/security-now/episodes/1088 https://twit.tv/shows/security-now/episodes/1088 Help & How To Technology Security no Ransomware Negotiations Go High-Tech openssl vulnerability, AI in cybersecurity, AI prompt injection, 1Password Claude integration, Bitwarden agentic AI access, ransomware AI usage, WordPress core vulnerability, Shadow AI, Wiz Security AI agents, remote code execution, credential management, Cybercriminals are harnessing AI not to break in, but to make sense of their stolen loot and increase their leverage in multi-million dollar ransomware heists. This episode unpacks how AI is now turbocharging extortion and negotiations on the dark side.

  • The "bone crushing" didn't happen this month.
  • Revisiting and inspecting July's Patch Tuesday.
  • A widespread and worrisome flaw in OpenSSL.
  • Claude can now access your 1Password credentials.
  • Bitwarden is aware that we need whole new security.
  • The day ends in "y" so a new prompt injection attack.
  • A true (and rare) core Wordpress emergency update.
  • Lots of interesting listener feedback.
  • And new ways AI is being used by bad guys

Show Notes - https://www.grc.com/sn/SN-1088-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> Cybercriminals are harnessing AI not to break in, but to make sense of their stolen loot and increase their leverage in multi-million dollar ransomware heists. This episode unpacks how AI is now turbocharging extortion and negotiations on the dark side.

  • The "bone crushing" didn't happen this month.
  • Revisiting and inspecting July's Patch Tuesday.
  • A widespread and worrisome flaw in OpenSSL.
  • Claude can now access your 1Password credentials.
  • Bitwarden is aware that we need whole new security.
  • The day ends in "y" so a new prompt injection attack.
  • A true (and rare) core Wordpress emergency update.
  • Lots of interesting listener feedback.
  • And new ways AI is being used by bad guys

Show Notes - https://www.grc.com/sn/SN-1088-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> Cybercriminals are harnessing AI not to break in, but to make sense of their stolen loot and increase their leverage in multi-million dollar ransomware heists. This episode unpacks how AI is now turbocharging extortion and negotiations on the dark side.

  • The "bone crushing" didn't happen this month.
  • Revisiting and inspecting July's Patch Tuesday.
  • A widespread and worrisome flaw in OpenSSL.
  • Claude can now access your 1Password credentials.
  • Bitwarden is aware that we need whole new security.
  • The day ends in "y" so a new prompt injection attack.
  • A true (and rare) core Wordpress emergency update.
  • Lots of interesting listener feedback.
  • And new ways AI is being used by bad guys

Show Notes - https://www.grc.com/sn/SN-1088-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> https://pdst.fm/e/pscrb.fm/rss/p/mgln.ai/e/294/cdn.twit.tv/megaphone/sn_1088/ARML9353215246.mp3 2:47:29 SN 1088: A Nefarious Novel Use for AI - Ransomware Negotiations Go High-Tech Ransomware Negotiations Go High-Tech openssl vulnerability, AI in cybersecurity, AI prompt injection, 1Password Claude integration, Bitwarden agentic AI access, ransomware AI usage, WordPress core vulnerability, Shadow AI, Wiz Security AI agents, remote code execution, credential management, nonadult tv-g IAB19 Steve Gibson Leo Laporte Steve Gibson Leo Laporte SN 1087: HalluSquatting, GhostApproval & GitLost - Patch Tuesday Breaks Records HalluSquatting, GhostApproval & GitLost - Patch Tuesday Breaks Records full TWiT Tue, 14 Jul 2026 19:14:03 PDT 1087 1087 https://twit.tv/shows/security-now/episodes/1087 https://twit.tv/shows/security-now/episodes/1087 Help & How To Technology Security no Patch Tuesday Breaks Records AI cybersecurity, Microsoft Patch Tuesday, Mythos Anthropic, autonomous agents, UK Cyber Shield, EU action plan on AI, HALU squatting, ghost approval, get lost exploit, Windows Defender vulnerabilities, child proofing iPhone, Assistive Access iOS AI is rewriting the rules of cybersecurity, and this week, massive government and private sector moves show just how quickly the stakes are rising. Find out how regulators, attackers, and defenders are all scrambling to keep up as vulnerabilities surface at record speed.

  • Europe warns their largest banks to prepare for AI attack.
  • The EU launches an action plan for AI Cybersecurity.
  • China considers keeping its budget AI to itself.
  • The UK's NCSC & GCHQ announce their "Cyber Shield".
  • CISA is using Mythos to audit U.S. government code.
  • Microsoft warns of their upcoming patch flood.
  • "RoguePlanet" receives an on-the-fly patch.
  • An underused mode to kid-proof an iPhone.
  • Listener feedback and three new AI attacks
  • HalluSquatting, GhostApproval & GitLost

Show Notes - https://www.grc.com/sn/SN-1087-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> AI is rewriting the rules of cybersecurity, and this week, massive government and private sector moves show just how quickly the stakes are rising. Find out how regulators, attackers, and defenders are all scrambling to keep up as vulnerabilities surface at record speed.

  • Europe warns their largest banks to prepare for AI attack.
  • The EU launches an action plan for AI Cybersecurity.
  • China considers keeping its budget AI to itself.
  • The UK's NCSC & GCHQ announce their "Cyber Shield".
  • CISA is using Mythos to audit U.S. government code.
  • Microsoft warns of their upcoming patch flood.
  • "RoguePlanet" receives an on-the-fly patch.
  • An underused mode to kid-proof an iPhone.
  • Listener feedback and three new AI attacks
  • HalluSquatting, GhostApproval & GitLost

Show Notes - https://www.grc.com/sn/SN-1087-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> AI is rewriting the rules of cybersecurity, and this week, massive government and private sector moves show just how quickly the stakes are rising. Find out how regulators, attackers, and defenders are all scrambling to keep up as vulnerabilities surface at record speed.

  • Europe warns their largest banks to prepare for AI attack.
  • The EU launches an action plan for AI Cybersecurity.
  • China considers keeping its budget AI to itself.
  • The UK's NCSC & GCHQ announce their "Cyber Shield".
  • CISA is using Mythos to audit U.S. government code.
  • Microsoft warns of their upcoming patch flood.
  • "RoguePlanet" receives an on-the-fly patch.
  • An underused mode to kid-proof an iPhone.
  • Listener feedback and three new AI attacks
  • HalluSquatting, GhostApproval & GitLost

Show Notes - https://www.grc.com/sn/SN-1087-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> https://pdst.fm/e/pscrb.fm/rss/p/mgln.ai/e/294/cdn.twit.tv/megaphone/sn_1087/ARML4251110087.mp3 2:48:51 SN 1087: HalluSquatting, GhostApproval & GitLost - Patch Tuesday Breaks Records Patch Tuesday Breaks Records AI cybersecurity, Microsoft Patch Tuesday, Mythos Anthropic, autonomous agents, UK Cyber Shield, EU action plan on AI, HALU squatting, ghost approval, get lost exploit, Windows Defender vulnerabilities, child proofing iPhone, Assistive Access iOS nonadult tv-g IAB19 Steve Gibson Leo Laporte Steve Gibson Leo Laporte SN 1086: The Apex Agentic Adversary - Visual Prompt Injection Strikes The Apex Agentic Adversary - Visual Prompt Injection Strikes full TWiT Tue, 07 Jul 2026 19:19:20 PDT 1086 1086 https://twit.tv/shows/security-now/episodes/1086 https://twit.tv/shows/security-now/episodes/1086 Help & How To Technology Security no Visual Prompt Injection Strikes Security Now, TWiT, steve gibson, Leo Laporte, Fable 5, AI security, agentic adversary, Vint Cerf retirement, Chrome 150, Google Chrome security updates, Opera Paste Protect, click-fix attacks, Microsoft Blue Hammer, FATFS vulnerabilities, Bug Bounty From the sudden retirement of Internet pioneer Vint Cerf to the unstoppable advance of "apex agentic adversaries," get a front-row seat to the unfolding security revolution and its massive real-world stakes.

  • Why Fable5's re-release has disappointed.
  • Opera becomes the first browser to offer "Paste Protect."
  • Microsoft BlueHammer exploit is "hammering" systems.
  • Industry legend (TCP creator) Vint Cerf on AI.
  • Chrome turns 150 with too many fixes to load.
  • Google fails to sidestep a $4.67 billion EU fine.
  • One last (we can hope) Chat Control vote next week.
  • AirDrop & Android Quick Share are exploitable.
  • How to bypass Claude's and ChatGPT's guardrails.
  • My own Sunday spin with SpinRite.
  • A legendary hacker uses AI on a widespread library

Show Notes - https://www.grc.com/sn/SN-1086-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> From the sudden retirement of Internet pioneer Vint Cerf to the unstoppable advance of "apex agentic adversaries," get a front-row seat to the unfolding security revolution and its massive real-world stakes.

  • Why Fable5's re-release has disappointed.
  • Opera becomes the first browser to offer "Paste Protect."
  • Microsoft BlueHammer exploit is "hammering" systems.
  • Industry legend (TCP creator) Vint Cerf on AI.
  • Chrome turns 150 with too many fixes to load.
  • Google fails to sidestep a $4.67 billion EU fine.
  • One last (we can hope) Chat Control vote next week.
  • AirDrop & Android Quick Share are exploitable.
  • How to bypass Claude's and ChatGPT's guardrails.
  • My own Sunday spin with SpinRite.
  • A legendary hacker uses AI on a widespread library

Show Notes - https://www.grc.com/sn/SN-1086-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> From the sudden retirement of Internet pioneer Vint Cerf to the unstoppable advance of "apex agentic adversaries," get a front-row seat to the unfolding security revolution and its massive real-world stakes.

  • Why Fable5's re-release has disappointed.
  • Opera becomes the first browser to offer "Paste Protect."
  • Microsoft BlueHammer exploit is "hammering" systems.
  • Industry legend (TCP creator) Vint Cerf on AI.
  • Chrome turns 150 with too many fixes to load.
  • Google fails to sidestep a $4.67 billion EU fine.
  • One last (we can hope) Chat Control vote next week.
  • AirDrop & Android Quick Share are exploitable.
  • How to bypass Claude's and ChatGPT's guardrails.
  • My own Sunday spin with SpinRite.
  • A legendary hacker uses AI on a widespread library

Show Notes - https://www.grc.com/sn/SN-1086-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

]]> https://pdst.fm/e/pscrb.fm/rss/p/mgln.ai/e/294/cdn.twit.tv/megaphone/sn_1086/ARML1942480908.mp3 2:53:23 SN 1086: The Apex Agentic Adversary - Visual Prompt Injection Strikes Visual Prompt Injection Strikes Security Now, TWiT, steve gibson, Leo Laporte, Fable 5, AI security, agentic adversary, Vint Cerf retirement, Chrome 150, Google Chrome security updates, Opera Paste Protect, click-fix attacks, Microsoft Blue Hammer, FATFS vulnerabilities, Bug Bounty nonadult tv-g IAB19 Steve Gibson Leo Laporte Steve Gibson Leo Laporte