AI Agents Hit Hundreds of Online Shops at ~$25 per Target, Researcher Reveals
cyb3rops · x · 2026-09-26
Security researcher Eyal revealed a real-world campaign where an operator gave an autonomous AI agent named Hermes hundreds of online shop targets to scan — some were later breached via a tool called Cairn — at an average reported cost of around $25 per target.
Key follow-up:
- Researcher @ChezDaniela hunted the skimmer side of the campaign
- Instead of chasing rotating C2 domains, she focused on stable characteristics of the injected code and its packer
- This expanded the hunt from one observed injection to 50+ affected shops
Takeaway for defenders: assume autonomous agents attacking online shops at scale for minimal cost is already happening, and pivot threat hunting toward stable code traits rather than mutable infrastructure.
More from Safety
- Running local open-source models? Dormant-neuron backdoors mean you may have let the right one in — DimitrisPapail · 2026-11-11
- Proving LLM backdoor-safety without revealing weights: ZKML over formal methods — DimitrisPapail · 2026-11-11
- OpenAI open-sources Codex Security CLI and SDK for AI-driven vulnerability scanning and fixing — openai · 2026-11-11
- Nando de Freitas: trusting models trained by others can be catastrophic, openness is essential for safe AI — DimitrisPapail · 2026-11-11
- Sayash Kapoor, Rishi Bommasani and Arvind Narayanan launch AI nonprofit STABL — random_walker · 2026-11-11
- UK regulator threatens universities with sanctions unless they adopt AI-proof exam formats — The Decoder · 2026-11-11