November 3, 2026 at 6:49 AM
We updated our AI agent incident tracker. This week:
A tampered Claude Code extension in Cursor’s marketplace for 11 hours
AGENTS.md in ~/Downloads steering Codex and Claude Code
Two critical RCE flaws in MCP Inspector
Every entry is sourced: node9.ai/incidents?w=...
#AISecurity #AISecurity
A tampered Claude Code extension in Cursor’s marketplace for 11 hours
AGENTS.md in ~/Downloads steering Codex and Claude Code
Two critical RCE flaws in MCP Inspector
Every entry is sourced: node9.ai/incidents?w=...
#AISecurity #AISecurity
AGENTS.md
AGENTS.md is a simple, open format for guiding coding agents. Think of it as a README for agents.
AGENTS.md
November 2, 2026 at 6:59 AM
We updated our AI agent incident tracker. This week:
A tampered Claude Code extension in Cursor’s marketplace for 11 hours
AGENTS.md in ~/Downloads steering Codex and Claude Code
Two critical RCE flaws in MCP Inspector
Every entry is sourced: node9.ai/incidents?w=...
#AISecurity #AISecurity
A tampered Claude Code extension in Cursor’s marketplace for 11 hours
AGENTS.md in ~/Downloads steering Codex and Claude Code
Two critical RCE flaws in MCP Inspector
Every entry is sourced: node9.ai/incidents?w=...
#AISecurity #AISecurity
Agentic breach at Chainalysis, a backdoored Claude Code extension and a ChatGPT link that could read private chats.
skillthropic.com
#AISecurity #infosec #cybersecurity
skillthropic.com
#AISecurity #infosec #cybersecurity
November 2, 2026 at 12:01 PM
Agentic breach at Chainalysis, a backdoored Claude Code extension and a ChatGPT link that could read private chats.
skillthropic.com
#AISecurity #infosec #cybersecurity
skillthropic.com
#AISecurity #infosec #cybersecurity
ALEX is the control and evidence layer for AI work.
#AI #ArtificialIntelligence #AISafety #AISecurity #Evidence #Verification #Transparency
#AI #ArtificialIntelligence #AISafety #AISecurity #Evidence #Verification #Transparency
November 1, 2026 at 1:54 PM
ALEX is the control and evidence layer for AI work.
#AI #ArtificialIntelligence #AISafety #AISecurity #Evidence #Verification #Transparency
#AI #ArtificialIntelligence #AISafety #AISecurity #Evidence #Verification #Transparency
Before using an AI tool with company information, understand where prompts go, how long they are retained, and whether they train future models. #AI #DataPrivacy #AISecurity
November 3, 2026 at 6:30 AM
Before using an AI tool with company information, understand where prompts go, how long they are retained, and whether they train future models. #AI #DataPrivacy #AISecurity
Before using AI with sensitive business information, understand where prompts are processed, how long they are retained, and who can access them. #AI #DataPrivacy #AISecurity
November 3, 2026 at 7:20 AM
Before using AI with sensitive business information, understand where prompts are processed, how long they are retained, and who can access them. #AI #DataPrivacy #AISecurity
Prompt injection is a data-boundary problem. Treat retrieved pages and uploaded documents as untrusted input: separate instructions from content, limit tool permissions, and test adversarial cases before connecting an agent to real workflows. #AISecurity #AIagents
November 2, 2026 at 8:56 AM
Prompt injection is a data-boundary problem. Treat retrieved pages and uploaded documents as untrusted input: separate instructions from content, limit tool permissions, and test adversarial cases before connecting an agent to real workflows. #AISecurity #AIagents
Anthropic Claude VS Code extension backdoored, affecting 5k developers. Cursor removed package
Sponsor this news channel today. https://www.ProNetGrowth.com/ai/?utm_source=bluesky&utm_medium=post&utm_campaign=news-ai&utm_content=ai
#AIsecurity #cybersecurity
Sponsor this news channel today. https://www.ProNetGrowth.com/ai/?utm_source=bluesky&utm_medium=post&utm_campaign=news-ai&utm_content=ai
#AIsecurity #cybersecurity
November 1, 2026 at 3:41 AM
Anthropic Claude VS Code extension backdoored, affecting 5k developers. Cursor removed package
Sponsor this news channel today. https://www.ProNetGrowth.com/ai/?utm_source=bluesky&utm_medium=post&utm_campaign=news-ai&utm_content=ai
#AIsecurity #cybersecurity
Sponsor this news channel today. https://www.ProNetGrowth.com/ai/?utm_source=bluesky&utm_medium=post&utm_campaign=news-ai&utm_content=ai
#AIsecurity #cybersecurity
When Your AI Agent Becomes the Incident: Who Has the Kill Switch?
youtu.be/NaYZlSQvWdU
#AgenticAI #AISecurity #Cybersecurity #AIGovernance #CyberRiskManagement
youtu.be/NaYZlSQvWdU
#AgenticAI #AISecurity #Cybersecurity #AIGovernance #CyberRiskManagement
October 30, 2026 at 8:10 PM
When Your AI Agent Becomes the Incident: Who Has the Kill Switch?
youtu.be/NaYZlSQvWdU
#AgenticAI #AISecurity #Cybersecurity #AIGovernance #CyberRiskManagement
youtu.be/NaYZlSQvWdU
#AgenticAI #AISecurity #Cybersecurity #AIGovernance #CyberRiskManagement
Thomas Laugle provides a Hall of Fame recommendation for 𝙏𝙝𝙚 𝘿𝙚𝙫𝙚𝙡𝙤𝙥𝙚𝙧’𝙨 𝙋𝙡𝙖𝙮𝙗𝙤𝙤𝙠 𝙛𝙤𝙧 𝙇𝙖𝙧𝙜𝙚 𝙇𝙖𝙣𝙜𝙪𝙖𝙜𝙚 𝙈𝙤𝙙𝙚𝙡 𝙎𝙚𝙘𝙪𝙧𝙞𝙩𝙮 by Steve Wilson
📝: cybercanon.org/the-develope...
#CyberCanonHallofFameNominee #CybersecurityBooks #AISecurity #LLM Security
📝: cybercanon.org/the-develope...
#CyberCanonHallofFameNominee #CybersecurityBooks #AISecurity #LLM Security
November 3, 2026 at 3:12 PM
Thomas Laugle provides a Hall of Fame recommendation for 𝙏𝙝𝙚 𝘿𝙚𝙫𝙚𝙡𝙤𝙥𝙚𝙧’𝙨 𝙋𝙡𝙖𝙮𝙗𝙤𝙤𝙠 𝙛𝙤𝙧 𝙇𝙖𝙧𝙜𝙚 𝙇𝙖𝙣𝙜𝙪𝙖𝙜𝙚 𝙈𝙤𝙙𝙚𝙡 𝙎𝙚𝙘𝙪𝙧𝙞𝙩𝙮 by Steve Wilson
📝: cybercanon.org/the-develope...
#CyberCanonHallofFameNominee #CybersecurityBooks #AISecurity #LLM Security
📝: cybercanon.org/the-develope...
#CyberCanonHallofFameNominee #CybersecurityBooks #AISecurity #LLM Security
Autonomy without controls isn't innovation. It's unmanaged risk with a product name.
✅ Agentic AI Security → www.amazon.com/dp/B0H3QZSTND
If this helped, share it with someone who's building or buying AI this year.
#AISecurity #AgenticAI #AIAgents #CyberSecurity #ThoughtLeadership
✅ Agentic AI Security → www.amazon.com/dp/B0H3QZSTND
If this helped, share it with someone who's building or buying AI this year.
#AISecurity #AgenticAI #AIAgents #CyberSecurity #ThoughtLeadership
https://www.amazon.com/dp/B0H3QZSTND
www.amazon.com
November 1, 2026 at 12:01 AM
Autonomy without controls isn't innovation. It's unmanaged risk with a product name.
✅ Agentic AI Security → www.amazon.com/dp/B0H3QZSTND
If this helped, share it with someone who's building or buying AI this year.
#AISecurity #AgenticAI #AIAgents #CyberSecurity #ThoughtLeadership
✅ Agentic AI Security → www.amazon.com/dp/B0H3QZSTND
If this helped, share it with someone who's building or buying AI this year.
#AISecurity #AgenticAI #AIAgents #CyberSecurity #ThoughtLeadership
The risky part of vibe-coded products is not the vibe coding.
It is shipping third-party packages, templates, auth snippets, and agent tools without checking what trust you just imported.
That is the gap CyberLens is built around. #BuildInPublic #AISecurity
It is shipping third-party packages, templates, auth snippets, and agent tools without checking what trust you just imported.
That is the gap CyberLens is built around. #BuildInPublic #AISecurity
October 31, 2026 at 11:20 PM
The risky part of vibe-coded products is not the vibe coding.
It is shipping third-party packages, templates, auth snippets, and agent tools without checking what trust you just imported.
That is the gap CyberLens is built around. #BuildInPublic #AISecurity
It is shipping third-party packages, templates, auth snippets, and agent tools without checking what trust you just imported.
That is the gap CyberLens is built around. #BuildInPublic #AISecurity
Most security advice starts too late: after the app exists.
For AI-native builders, the first question is earlier:
What are you about to trust?
A repo, website, package, skill, browser extension, API wrapper - all of it becomes your attack surface. #AISecurity
For AI-native builders, the first question is earlier:
What are you about to trust?
A repo, website, package, skill, browser extension, API wrapper - all of it becomes your attack surface. #AISecurity
November 3, 2026 at 3:20 PM
Most security advice starts too late: after the app exists.
For AI-native builders, the first question is earlier:
What are you about to trust?
A repo, website, package, skill, browser extension, API wrapper - all of it becomes your attack surface. #AISecurity
For AI-native builders, the first question is earlier:
What are you about to trust?
A repo, website, package, skill, browser extension, API wrapper - all of it becomes your attack surface. #AISecurity
US scrutiny of AI security widens from staffing concerns to hardware vulnerabilities
#Akerix #AI #AISecurity #HardwareVulnerabilities
https://akerix.com/article/ai-national-security?5w=1
#Akerix #AI #AISecurity #HardwareVulnerabilities
https://akerix.com/article/ai-national-security?5w=1
October 30, 2026 at 9:04 PM
US scrutiny of AI security widens from staffing concerns to hardware vulnerabilities
#Akerix #AI #AISecurity #HardwareVulnerabilities
https://akerix.com/article/ai-national-security?5w=1
#Akerix #AI #AISecurity #HardwareVulnerabilities
https://akerix.com/article/ai-national-security?5w=1
A file in a Downloads folder, dressed up as engineering notes. Coding agents follow AGENTS.md. One section said install an npm package that runs a Windows payload. This is called a poisoned agents file. Sunglasses scans it first. Via The Hacker News.
sunglasses.dev
#AIsecurity #PromptInjection
sunglasses.dev
#AIsecurity #PromptInjection
November 1, 2026 at 9:06 PM
A file in a Downloads folder, dressed up as engineering notes. Coding agents follow AGENTS.md. One section said install an npm package that runs a Windows payload. This is called a poisoned agents file. Sunglasses scans it first. Via The Hacker News.
sunglasses.dev
#AIsecurity #PromptInjection
sunglasses.dev
#AIsecurity #PromptInjection
How much authority should your AI agents have, and how will you know when something goes wrong?
Join this Virtual #AISummit for practical insights on #AIAgent security, governance, and responsible adoption, including a workshop on planning for Sovereign AI in 2027.
bit.ly/4sa4Mwt
#AISecurity
Join this Virtual #AISummit for practical insights on #AIAgent security, governance, and responsible adoption, including a workshop on planning for Sovereign AI in 2027.
bit.ly/4sa4Mwt
#AISecurity
November 2, 2026 at 11:32 PM
How much authority should your AI agents have, and how will you know when something goes wrong?
Join this Virtual #AISummit for practical insights on #AIAgent security, governance, and responsible adoption, including a workshop on planning for Sovereign AI in 2027.
bit.ly/4sa4Mwt
#AISecurity
Join this Virtual #AISummit for practical insights on #AIAgent security, governance, and responsible adoption, including a workshop on planning for Sovereign AI in 2027.
bit.ly/4sa4Mwt
#AISecurity
Un agent est sorti trois fois d'une VM QEMU/KVM : la VM n'est plus une frontière blog.gioria.org/fr/ai-securi... #AISecurity
November 2, 2026 at 10:42 AM
Un agent est sorti trois fois d'une VM QEMU/KVM : la VM n'est plus une frontière blog.gioria.org/fr/ai-securi... #AISecurity
Cette semaine : des logs pris pour des ordres, une gateway IA au KEV, et deux binaires piégés aux identités valides blog.gioria.org/fr/cybersec/... #AISecurity
November 2, 2026 at 7:42 AM
Cette semaine : des logs pris pour des ordres, une gateway IA au KEV, et deux binaires piégés aux identités valides blog.gioria.org/fr/cybersec/... #AISecurity
Good reminder: treat prompts like any other data-sharing channel. Keep credentials, customer records and confidential code out, and use approved tools with clear retention controls. #AISecurity
November 2, 2026 at 5:59 PM
Good reminder: treat prompts like any other data-sharing channel. Keep credentials, customer records and confidential code out, and use approved tools with clear retention controls. #AISecurity
60,000 requests disguised as normal traffic. Daishin Securities says 38,490 customers' data leaked via a partner-linked server. https://www.koreaherald.com/article/10917639 #infosec #AIsecurity enforceauth.com
November 3, 2026 at 4:39 PM
60,000 requests disguised as normal traffic. Daishin Securities says 38,490 customers' data leaked via a partner-linked server. https://www.koreaherald.com/article/10917639 #infosec #AIsecurity enforceauth.com
That's a wrap on Security Field Day #XFD16!
Thank you #Aviatrix for presenting. Videos will be posted soon to YouTube and our website!
▶️ YouTube: youtube.com/@techfieldday
@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
Thank you #Aviatrix for presenting. Videos will be posted soon to YouTube and our website!
▶️ YouTube: youtube.com/@techfieldday
@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
October 30, 2026 at 10:15 PM
That's a wrap on Security Field Day #XFD16!
Thank you #Aviatrix for presenting. Videos will be posted soon to YouTube and our website!
▶️ YouTube: youtube.com/@techfieldday
@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
Thank you #Aviatrix for presenting. Videos will be posted soon to YouTube and our website!
▶️ YouTube: youtube.com/@techfieldday
@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
Security Field Day #XFD16 continues now! 🔐
Tune in 🔴 LIVE to see #ForwardNetworks present on YouTube and LinkedIn.
▶️ YouTube: www.youtube.com/@techfieldday
🔹 Linkedin: www.linkedin.com/company/tech...
@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
Tune in 🔴 LIVE to see #ForwardNetworks present on YouTube and LinkedIn.
▶️ YouTube: www.youtube.com/@techfieldday
🔹 Linkedin: www.linkedin.com/company/tech...
@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
October 29, 2026 at 9:28 PM
Security Field Day #XFD16 continues now! 🔐
Tune in 🔴 LIVE to see #ForwardNetworks present on YouTube and LinkedIn.
▶️ YouTube: www.youtube.com/@techfieldday
🔹 Linkedin: www.linkedin.com/company/tech...
@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
Tune in 🔴 LIVE to see #ForwardNetworks present on YouTube and LinkedIn.
▶️ YouTube: www.youtube.com/@techfieldday
🔹 Linkedin: www.linkedin.com/company/tech...
@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
So scary even your dusty cooch granny will clench... & it'll still perceive it as a threat. #running #securitychecks today. I had a really hard gas bubble a second ago... & the AI security registered it as a threat. 😐✍️📖🐈⬛
#mustashe #AIsecurity #overheadsecurity #worstimaginationever
#mustashe #AIsecurity #overheadsecurity #worstimaginationever
October 30, 2026 at 10:57 PM
So scary even your dusty cooch granny will clench... & it'll still perceive it as a threat. #running #securitychecks today. I had a really hard gas bubble a second ago... & the AI security registered it as a threat. 😐✍️📖🐈⬛
#mustashe #AIsecurity #overheadsecurity #worstimaginationever
#mustashe #AIsecurity #overheadsecurity #worstimaginationever
Interesting reminder that model assurance depends on the whole stack. Hardware integrity checks and end-to-end validation belong alongside model testing. #AISecurity #AISafety
November 1, 2026 at 5:38 AM
Interesting reminder that model assurance depends on the whole stack. Hardware integrity checks and end-to-end validation belong alongside model testing. #AISecurity #AISafety
Security Field Day #XFD16 continues now! 📅 October 30, 2026 🔐
Tune in 🔴 LIVE to see #Aviatrix present.
▶️ YouTube: youtube.com/@techfieldday
🔹 Linkedin: linkedin.com/company/tech...
@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
Tune in 🔴 LIVE to see #Aviatrix present.
▶️ YouTube: youtube.com/@techfieldday
🔹 Linkedin: linkedin.com/company/tech...
@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
October 30, 2026 at 8:28 PM
Security Field Day #XFD16 continues now! 📅 October 30, 2026 🔐
Tune in 🔴 LIVE to see #Aviatrix present.
▶️ YouTube: youtube.com/@techfieldday
🔹 Linkedin: linkedin.com/company/tech...
@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
Tune in 🔴 LIVE to see #Aviatrix present.
▶️ YouTube: youtube.com/@techfieldday
🔹 Linkedin: linkedin.com/company/tech...
@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity