Inside the AI Agent Hacking Campaign: Exposed Cairn Panels Let Researchers Watch Attacks Live
aakashgupta · x · 2026-11-06
Sources and full reporting behind the weekly AI security recap: NorForge researcher Snorre Fagerland found 24 malicious instances of Cairn, an open-source AI pentesting tool, exposed on the public internet, letting him watch the attackers' agents work in real time. Cairn sets agents a starting point and goal, with operators adding hints along the way. Reuters identified victims from the attacker's own records; data theft remains unknown. The tool's author le1xia0 says misuse wasn't intended.
Related event: Hacker Uses Autonomous AI Agent to Breach 1,200+ Websites for About $5,000(2 posts)→
More from Safety
- AG Szpunar opinion in Like Company v Google: training Gemini on news articles is copyright-relevant reproduction — technollama · 2026-11-06
- Bug bounty hunters filed tens of millions of vulns, big firms share maybe 1% — rez0__ · 2026-11-06
- LSEG cuts 5-year market backtest from hours to ~1 minute; Tampa General adds AI safety gate — NVIDIAAI · 2026-11-06
- Tampa General post-trains NVIDIA Nemotron to screen AI calls for prompt injection — NVIDIAAI · 2026-11-06
- DeepMind's 'Keeping Defenders Ahead' Page Displays Root CA Passwords Everywhere — m4rkmc · 2026-11-06
- Anthropic urged regulation then balked at real commitments, says policy expert — peterwildeford · 2026-11-06