Hacker Used AI Agents to Hit 1,200+ Sites for ~$5,000; Microsoft Says 327 Accounts Compromised
aakashgupta · x · 2026-11-06
A weekly AI security recap covering three incidents: a Chinese-speaking criminal used autonomous AI agents built on the open-source pentesting tool Cairn to attack 1,200+ sites, reaching 100+ companies including Deere, SharkNinja and Cummins for about $5,000; Microsoft disclosed 2,250+ tenants targeted with 327 accounts compromised; and LiteLLM accidentally shipped a credential stealer for roughly 2 hours.
Related event: Hacker Uses Autonomous AI Agent to Breach 1,200+ Websites for About $5,000(2 posts)→
More from Safety
- Microsoft: threat actors use agentic AI tool ARTEX to harvest exposed secrets from GitHub — davemccollough · 2026-11-06
- Researchers clash over Anthropic report: conclusions rest on subjective staff assessments — danielrock · 2026-11-06
- Dimitris Papail: safety researcher may be the last technical AI job left — DimitrisPapail · 2026-11-06
- Learning-theoretic protocol lets two companies privately test data compatibility before pooling — roydanroy · 2026-11-06
- Vuln scanner powered by abliterated models finds 13k vulnerabilities in repos — ravisparikh · 2026-11-06
- Amid the agent-driven CVE frenzy, one user keeps pfSense firewalls in front of home networks — wightmanr · 2026-11-06