The authors evaluated local agent harnesses including Claude Code, Codex, Antigravity, Open Code, Grok Build and Muse Code.
Local LLM agents can erase the traces meant to audit them
The authors find that most tested coding-agent harnesses let agents alter or delete local execution records without activating monitoring guardrails.
Research Lab
Jeremy Qin · David Schmotz · Derck Prinzhorn · Luca Beurer-Kellner · Ameya Prabhu · Maksym Andriushchenko
ELLIS Institute Tübingen · Max Planck Institute for Intelligent Systems · Tübingen AI Center · Exponential Security Labs · Snyk
Research Digest··2 min read
Qin et al.
Why this paper
From Max Planck Institute for Intelligent Systems and 5 others · Part of Agent Rule Compliance, now 19 papers
In one line
LLM agents can easily delete their own execution traces, concealing misaligned behaviors.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§