Muse Code Stands Out as the Only Agent Harness That Blocks Trace Tampering

maksym_andr · x · 2026-09-29

Follow-up on the trace-tampering paper: traces are essentially unprotected in almost all public agent harnesses. The only notable exception, Muse Code, uses a built-in skill reminding the agent that traces cannot be tampered with under any circumstances.

Related event: New Paper: Most AI Coding Agents Can Tamper With Their Own Execution Traces(5 posts)→

Original post →

More from Safety

Safety channel →