AI agents attacking Amazon's LLM honeypots leaked their full campaign memory, stolen API keys
AccBalanced · x · 2026-11-16
Amazon set up decoy servers posing as LLM APIs, and attackers' AI agents ended up sending their entire campaign memory — system prompts, tool histories, shared knowledge graphs, and logged findings — straight to them. Amazon's MadPot sensors caught traffic from ARTEX, an open-source agentic pentest framework, between October 3 and November 5.
The standout campaign was credential theft: agents targeted self-hosted AI gateways and app builders like LiteLLM, One API, Dify, Langflow, Open WebUI, and Ollama, extracted the provider API keys stored inside, verified which ones still worked, then fed the stolen keys back into their own model calls — effectively funding their operation with victims' accounts.
It's a vivid sign that the cyber attack kill chain is entering an agent-driven era, with LLM honeypots emerging as a new defensive tool.
Related event: Amazon Honeypot Tricks Hacker AI Agents Into Leaking Attack Memory(2 posts)→
More from coding & agent
- Quant researcher co-writes a short math-heavy book on agentic engineering with LLMs — blaizedsouza · 2026-11-16
- llm-council built into Hermes: multiple models answer, blind-rank, and a chairman decides — Scobleizer · 2026-11-16
- Grok Build v1.0.87 improves multi-agent workflows, MCP panel and session search — XFreeze · 2026-11-16
- Swarm orchestration runs 12 parallel agents to build a Blender 3D model, claims tester — venturetwins · 2026-11-16
- AgentWeb lands YC W27 spot building endpoints that let AI agents operate any site — damnGruz · 2026-11-16
- Prototype pairs kids' code, a real robot and Snap Spectacles AR for learning — stspanho · 2026-11-16