No AI summary available for this article.
Why It Matters
Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own execution traces. We show that local LLM agents such as Claude Code, Codex, Antigravity, Open Code and Grok Build fail to enforce this boundary. All tested harnesses, except Muse Code, allowed agents to delete their traces when asked, without triggering monitor guardrails. We also validate that external attackers can exploit this gap to induce trace deletion. Finally, we show that trace tampering...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.30266v1 · Indexed about 1 hour ago