One of my internet-exposed inference honeypots was discovered, relabeled with sought-after model names, and incorporated into infrastructure apparently used to provide "free" LLM backends. It then received a real coding-agent session &#;x26;#;xe2;&#;x26;#;x80;&#;x26;#;x94; history, filesystem output, working paths, and the agent&#;x26;#;39;s local tool manifest. The honeypot did not request or cause any tool execution; what the request exposed is what a malicious operator in that position could do.
This article has been indexed from SANS Internet Storm Center, InfoCON: green
Read the original article: