AI Agents Breach Dozens of Orgs, Steal ~600k Credit Cards in First Scaled Agentic Cyberattack
deanwball · x · 2026-09-23
Security researchers have disclosed a massive, ongoing criminal campaign using Cairn, an autonomous penetration-testing harness, and other AI agents to attack hundreds of organizations, breaching at least tens of them — up to 25 attacked simultaneously at peak.
Key findings:
- Financially motivated; 600k unexpired credit cards stolen
- The system coordinated several harnesses with inference via OpenRouter
- Observed models: GLM 5.2, DeepSeek V4 Pro, DeepSeek V4.1 Flash, and Opus 4.6 (opus guardrails lagged later models)
- Minimal human nudging kept agents going, vibe-coding style
- Agents mostly exploited unglamorous web app vulns, but chose each attack path in real time via extensive probing, yielding dynamic, mostly unique TTPs
Described as the best example yet of attackers scaling cyber operations with agents; interim report published.
More from AGI Musings
- OpenAI, Anthropic and DeepMind job posts signal PMs must write evals and code — aakashgupta · 2026-11-12
- Architecture study sparks monitoring concerns over a multi-hop planning spike — ChowdhuryNeil · 2026-11-12
- PowerShell creator Jeffrey Snover at Ignite: AI revolution is an extinction event for those who don't adapt — dfinke · 2026-11-12
- Worst AI use: signaling you don't care about things you should — Afinetheorem · 2026-11-12
- Stanford HAI blueprint: 56 US agencies report 3,611 AI use cases, evaluation lags — StanfordHAI · 2026-11-12
- Fleuret amplifies debate: AI can't slash wet-lab experiments in unmapped biology — francoisfleuret · 2026-11-12