1,300+ Exposed AI Pentest Harnesses Found Online as ARTEX, Cairn, PentAGI Power Real Intrusions
cyb3rops · x · 2026-11-04
RST Labs reports that open-source AI agent harnesses Cairn, ARTEX and PentAGI are powering real-world intrusions: Microsoft saw Storm-0940 use ARTEX to attempt sign-ins across 2,250+ tenants after the ConnectWise compromise, with privileged cloud access gained within 3 hours in multiple attacks; CrowdStrike tracked VAPOR PANDA hitting 200+ organizations; one Cairn operator burned 36.7B tokens targeting governments in 4 countries.
No new exploits needed—just orchestrators that split goals into LLM agent tasks running around the clock. As of Nov 2, 2026, over 1,300 internet-exposed consoles for these harnesses were verified across Shodan and Netlas. The article details stack, default ports and auth (Cairn ships with none), plus hunting queries for each.
More from Safety
- Reminder: You're legally liable for your AI agents' actions — 'whoops' won't hold up in court — var_epsilon · 2026-11-04
- CrowdStrike unveils AI Kill Switch to give humans runtime control over AI agents — AccBalanced · 2026-11-04
- Tracking which AI tools can access sensitive data is an unsolved enterprise headache — Ian-Cubeless · 2026-11-04
- Dataset of 2k+ LLM chats with real voters released to build better decision evals — logangraham · 2026-11-04
- Reuters: OpenAI Staff Warned for Years About Security Lapses in Its Monorepo — rohanpaul_ai · 2026-11-04
- Interview: how AI is changing the economics of privacy — _ghnn_ · 2026-11-04