Skip to content

AI security tracker

AI security incidents, vulnerabilities, and research, newest first. Each line links to a summary page and to the original source.

November 2026

  1. Nov 21 Signal Agent and tool abuse Source

    Signal blocks screenshots by default on iOS 27 and Android to stop Siri AI and Gemini agents from reading private chats

    Privacy is our mission; it’s why we exist, and we do everything we can to protect it. This means that we are restricting the latest AI agents built into mobile operating systems from potentially capturing and storing your Signal data.

  2. Nov 20 Security Boulevard Agent and tool abuse Source

    Google built Mirror Dimension, a simulated internet with fake banks and stores, to test Chrome AI agents against attacks

    Google’s new Mirror Dimension uses thousands of simulated websites to test Chrome AI agents against security threats, highlighting the growing need for rigorous safeguards as enterprises adopt autonomous AI workflows. #AgenticAI...

  3. Nov 20 The Decoder Other Source

    OpenAI makes it much harder for attackers to extract how its latest AI models think

    OpenAI has significantly strengthened safeguards against extracting internal reasoning from GPT-6.2 Astra and GPT-6.2 Sol. In adaptive red-teaming tests, the success rate for extracting protected reasoning fell from 54 percent to 0.2...

  4. Nov 20 Metacurity Other Source

    GAO audit: Claude, Grok, ChatGPT and Gemini produced terror attack and power-grid plans within 12 hours after testers bypassed safeguards

    Claude, Grok, ChatGPT and Gemini produced detailed mass-casualty or power-grid attack plans within 12 hours after testers bypassed safeguards, the watchdog found. The companies say their protections have since evolved.

  5. Nov 20 Dragos Other Source

    Dragos seeded 2 million canary credentials into AI prompts and caught attackers stealing data at three AI inference providers

    We seeded two million AI prompts with canary tokens and found three provider breaches, prompt theft, and ignored Zero Data Retention settings.

  6. Nov 20 BleepingComputer Agent and tool abuse Data exposure Source

    Bell Canada says an agentic AI attacker breached its circuit-ordering system and stole enterprise customer data

    Bell Canada has confirmed that an "agentic" threat actor breached its systems on November 17, 2026, and stole enterprise customer data, including information from a system used to order and provision telecommunications circuits.

  7. Nov 20 BleepingComputer Vulnerability Source

    Hackers use autonomous AI tool Cairn to find zero-day, take over server

    Threat actors used the open-source AI penetration-testing framework Cairn to find a previously unknown vulnerability in a medical imaging application.

  8. Nov 20 The Register Agent and tool abuse Vulnerability Source

    China attackers deployed AI agents that autonomously found and exploited a 0-day to take over a university server

  9. Nov 20 The Decoder Agent and tool abuse Source

    An OpenAI agent assigned a simple writing task decided on its own to build a secret email surveillance tool

    An internal OpenAI model was supposed to create a fitness document but instead began planning scripts to secretly forward emails to an "attacker." The agent recognized the conflict with its assigned task but dismissed it as an...

  10. Nov 19 The Record Model misuse Source

    European Commission confirms cyberattack, says hackers used AI tool

    POLITICO had reported CERT-EU had identified the attackers’ use of ARTEX, an open-source AI hacking platform that the FBI last week warned was being used both by criminals and state-sponsored groups.

  11. Nov 19 9to5Mac Data exposure Source

    Major privacy breaches reported in Muse AI, including bank balances

    Meta employees have expressed concerns about what appear to be major privacy breaches when using Muse, currently the second most...

  12. Nov 19 CyberSecurityNews Other Source

    AI hacking framework CyberStrikeAI ran 221 tool executions in one session with no human approval

  13. Nov 19 RiskyBiz Policy and legal Source

    Phew! Some Regulatory Relief for AI Hacks

  14. Nov 18 Help Net Security Vulnerability Source

    Ubuntu Pro customers can now install AI-written security patches from an opt-in Edge archive before human review

    Ubuntu AI security patches now reach Pro users early through the opt-in Edge archive, before Canonical finishes testing and qualifying them.

  15. Nov 18 TechCrunch Agent and tool abuse Source

    More banks say customers using AI agents are on their own even if they get hacked

    Citi is the latest major financial institution to put the breaks on personal finance AI agents.

  16. Nov 17 CNBC Policy and legal Source

    LeBron James sues startup over viral AI ad allegedly exploiting his likeness

    LeBron James sued an AI-powered sports betting startup over alleged unauthorized use of his likeness.

  17. Nov 17 CyberScoop Vulnerability Research Source

    A vulnpocalypse bug worthy of attention: Researchers disclose critical flaw in Java with help of AI

    Researchers at Calif used AI to uncover Java4Shell (CVE-2026-114938), a critical OpenJDK memory-corruption flaw patched by Oracle on Tuesday.

  18. Nov 17 Varonis Phishing and fraud Source

    Varonis identifies TheMailer, a self-hosted phishing kit that uses Claude and ChatGPT to rewrite lures until they pass spam filters

    TheMailer is a popular self-hosted phishing platform that runs on AI models like Claude and ChatGPT, going beyond writing lures to tailor them to each mail provider and rewrite them until they bypass spam filters.

  19. Nov 17 BleepingComputer Supply chain Research Source

    Researchers hijack Hugging Face account for popular Kokoro AI model

    A Lack of ownership verification on the Hugging Face platform allowed researchers to take control of Kokoro, a text-to-speech model used in projects from Google, NVIDIA, AMD, Intel, and Amazon Web Services.

  20. Nov 17 The Hacker News Malware Phishing and fraud Source

    Trigram Campaign Impersonates About 50 AI and Blockchain Brands to Target Devs with Infostealers

    Trigram impersonates about 50 AI and blockchain brands, using phishing and trojanized code to lure developers into running infostealers.

  21. Nov 17 The Register Other Source

    Hackers smash ’n’ grab AI vendor: Take off with license data of Uber drivers

  22. Nov 17 SecurityWeek Vulnerability Model misuse Source

    AI Framework Autonomously Weaponized Flaws in Real Attacks, Google Says

    GTIG has observed APTs and cybercrime groups increasingly adopting generative AI across operations, including multi-agent frameworks.

  23. Nov 17 BleepingComputer Vulnerability Source

    Anthropic Claude Fable 5.2 blocks fewer security tasks, while Mythos 5.2 gets better at finding bugs

    Anthropic recently rolled out Claude Mythos 5.2 to selected partners and Fable 5.2 to regular users, with improvements to coding and reasoning. But we also noticed some interesting cybersecurity changes.

  24. Nov 17 CyberSecurityNews Other Source

    Claude helps a car owner crack a 32-year-old Jeep engine computer with a $3 Arduino

  25. Nov 17 CyberSecurityNews Malware Source

    Claude can now pull VirusTotal threat intelligence into malware and URL investigations

  26. Nov 17 Help Net Security Vulnerability Source

    AI models found security flaws in discontinued devices that no vendor is left to patch

    Forescout researchers built a tool to test if generally available AI models could find security flaws on a limited budget. They examined both open-source

  27. Nov 17 BleepingComputer Vulnerability Source

    Google Project Zero cuts its bug disclosure deadline to 30 days as AI speeds up exploitation

    Google Project Zero will replace its "90+30" disclosure policy with shorter, fixed deadlines in response to AI-accelerated vulnerability discovery and exploitation.

  28. Nov 17 Anthropic Vulnerability Source

    Anthropic shortens its vulnerability disclosure window from 90 to 30 days as AI speeds up exploitation

    We’re shortening our vulnerability disclosure window from 90 days to 30 days for high- and critical-severity issues, and to 45 days for all other issues.

  29. Nov 17 CyberSecurityNews Agent and tool abuse Source

    Windows 11 quietly tracks which AI coding agents developers run, including Claude, Codex, Copilot and Cursor

  30. Nov 16 BleepingComputer Agent and tool abuse Source

    Gemini agents bypassed safeguards and attacked Epoch AI live website during safety testing

    Google's Gemini AI agents repeatedly attempted to hack a real organization's website during AI model safety testing, finding ways to circumvent increasingly restrictive security controls designed to prevent them from accessing live systems.

  31. Nov 16 The Register Agent and tool abuse Source

    Attackers are using AI agents to automate cybercrime at ’industrial scale,’ FBI and AWS warn

  32. Nov 16 CyberScoop Agent and tool abuse Policy and legal Source

    California sues OpenAI over AI agents’ summer hacking spree

    California Attorney General Rob Bonta sued OpenAI, accusing it of obstructing investigations into agentic AI hacks and lacking proper safeguards.

  33. Nov 16 CyberScoop Model misuse Source

    Google says Russian-speaking hackers ran the first fully automated AI cyberattack

    Google’s Threat Intelligence Group says Russian-speaking hackers used an AI system dubbed exploit_agent to run the first fully automated cyberattack.

  34. Nov 16 The Hacker News Agent and tool abuse Vulnerability Source

    Google Finds Hackers Using AI Agents to Build and Run Exploits From Software Patches

    Google reports threat actors using autonomous AI frameworks in live intrusions, accelerating vulnerability weaponization and phishing operations.

  35. Nov 14 BleepingComputer Data exposure Source

    Cursor confirms a leaked Fireworks AI key let attackers publish a backdoored Claude Code extension

    Cursor confirmed it suffered a security breach that let hackers distribute a malicious Claude Code extension through its marketplace after stealing credentials from AI infrastructure provider Fireworks AI.

  36. Nov 14 WiredAI Malware Source

    Beware the New AI-Fueled Ransomware Boom

    Fully automated ransomware hasn’t arrived, yet. But seemingly unsophisticated attackers are using AI tools to wreak havoc.

  37. Nov 12 Unit42 Data exposure Source

    Attackers used open-source Cairn AI to breach semiconductor and defense targets

    Our analysis of how attackers used the open-source Cairn AI agent framework to autonomously breach semiconductor, defense and civic targets.

  38. Nov 12 The Record Agent and tool abuse Source

    Kazakhstan-linked hackers used AI agent to spy on Central Asian governments

    Suspected Kazakhstan-linked hackers used an artificial intelligence agent to help spy on Central Asian governments, steal sensitive documents and infiltrate critical infrastructure networks, according to new research.

  39. Nov 12 Help Net Security Data exposure Source

    Stolen Claude API keys can turn Claude Code into a remote-controlled implant

    Darktrace used stolen Claude API keys to steer Claude Code through memory stores in a lab, exfiltrating a 1 GB file via Anthropic’s own API.