#aisecurity
LightNews LightNews
nawi-n9.bsky.social
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
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
skillthropic.com
Agentic breach at Chainalysis, a backdoored Claude Code extension and a ChatGPT link that could read private chats.

skillthropic.com

#AISecurity #infosec #cybersecurity
November 2, 2026 at 12:01 PM
alexosautonom.bsky.social
ALEX is the control and evidence layer for AI work.

#AI #ArtificialIntelligence #AISafety #AISecurity #Evidence #Verification #Transparency
November 1, 2026 at 1:54 PM
pillai.wsocial.eu
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
cybersecboardrm.bsky.social
When Your AI Agent Becomes the Incident: Who Has the Kill Switch?
youtu.be/NaYZlSQvWdU
#AgenticAI #AISecurity #Cybersecurity #AIGovernance #CyberRiskManagement
October 30, 2026 at 8:10 PM
ainewsbulletin.bsky.social
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
November 1, 2026 at 3:41 AM
filesigsec.bsky.social
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
https://www.amazon.com/dp/B0H3QZSTND
www.amazon.com
November 1, 2026 at 12:01 AM
akerix-en.bsky.social
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
October 30, 2026 at 9:04 PM
cyberlensai.bsky.social
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
October 31, 2026 at 11:20 PM
techfieldday.com
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
October 29, 2026 at 9:28 PM
techfieldday.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
October 30, 2026 at 10:15 PM
twitchingdeadgirl.bsky.social
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
October 30, 2026 at 10:57 PM
sunglassesdev.bsky.social
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
November 1, 2026 at 9:06 PM
techfieldday.com
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
October 30, 2026 at 8:28 PM
spoint42.bsky.social
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
savilltech.com
Overview of key Microsoft security solutions to accelerate security defense in the age of AI.

youtu.be/dSODQy9bWjU

#MicrosoftSecurity #CyberSecurity #AISecurity #AIForSecurity #MicrosoftDefender #SecurityOperations #ThreatIntelligence #IncidentResponse #SecureAI #CyberDefense
Accelerating Defense with Microsoft Security Solutions
YouTube video by John Savill's Technical Training
youtu.be
October 28, 2026 at 8:48 AM
techfieldday.com
Security Field Day #XFD16 continues tomorrow at 8:00 AM! 📅 October 30, 2026 🔐

Thank you for presenting #ForwardNetworks! Videos will be posted to YouTube and our website soon.

▶️ YouTube: www.youtube.com/@techfieldday

@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
October 29, 2026 at 11:15 PM
dofthings.bsky.social
AI Found Four Industrial Security Flaws in Four Hours. Now What? www.theregister.com/security/202... #ai #artificialintelligence #software #aigovernance CTO #CEO #CDO #CIO #aisecurity #cybersecurity #cybercrime #aiagent #aiagents
October 29, 2026 at 5:03 PM
spoint42.bsky.social
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
exponential-e.bsky.social
AI security goes beyond suspicious words! Robin Johns reveals how analysing context and intent can expose threats that traditional security tools miss.

▬ CX Meets - Podcast Ep 07 Part 2 ▬
https://www.youtube.com/watch?v=zU2_iNaD2N8

#ExponentialE #AISecurity #IntentMonitoring #CyberSecurity #AI
October 31, 2026 at 10:02 AM
techfieldday.com
Are you watching #AWS at Security Field Day #XFD16?

Tune in 🔴 LIVE and leave your comments and questions in chat!

▶️ YouTube: youtube.com/@techfieldday
🔹 Linkedin: linkedin.com/company/tech...

@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity #AWS
October 30, 2026 at 5:27 PM
techfieldday.com
Security Field Day #XFD16 continues in 30 minutes!

Tune in 🔴 LIVE at 1:30 PM US/Pacific Time to see #Aviatrix present.

▶️ YouTube: youtube.com/@techfieldday
🔹 Linkedin: linkedin.com/company/tech...

@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
October 30, 2026 at 8:03 PM
pillai.wsocial.eu
This is a reminder that model reliability depends on the full stack: hardware integrity, supply-chain controls, and independent validation all matter. #AISecurity #TrustworthyAI
November 1, 2026 at 7:12 AM
techfieldday.com
Security Field Day #XFD16 continues soon!

Thank you #HPENetworking for presenting. Videos will be posted soon to YouTube and our website!

▶️ YouTube: www.youtube.com/@techfieldday

@TechFieldDay.com @NetworkingNerd.net #XFD16 #Cybersecurity #AISecurity
October 29, 2026 at 7:45 PM
cyberlensai.bsky.social
Before you plug a new AI coding tool into your workflow, inspect what it can touch: repo, shell, browser, secrets, package manager, deployment path. The permission model matters more than the demo. #AISecurity #DevSecOps
October 28, 2026 at 2:20 PM