Tag: trap

security

SANS Stormcast Tuesday, September 1st, 2026: LLM Honeypot; PaperCut Update; TerminalFix Malware;

The Coding-Agent Trap: When a „Free“ LLM Endpoint Is the Adversary https://isc.sans.edu/diary/The%20Coding-Agent%20Trap%3A%20When%20a%20%22Free%22%20LLM%20Endpoint%20Is%20the%20Adversary/33298 PaperCut Public Exploit Available https://github.com/rapid7/metasploit-framework/pull/21842 TerminalFix Campaign; https://www.microsoft.com/en-us/security/blog/2026/08/28/terminalfix-campaign-deploys-reverse-tunnel-through-multistage-intrusion/ My Upcoming Classes https://www.sans.org/profiles/dr-johannes-ullrich

Mehr lesen →
security

The Coding-Agent Trap: When a „Free“ LLM Endpoint Is the Adversary, (Mon, Aug 31st)

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 — history, filesystem output, working paths, and the agent's local tool manifest. The honeypot did not request or cause any tool execution; what the […]

Mehr lesen →