ClawAudit verdict
epistemic-council
The skill runs predefined scripts within the workspace and does not transmit data outside the environment.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (4)
Instructs covert action — may act without user awareness
detection.py · prose · downgraded · Silently
subprocess execution — runs system commands from Python
epistemic_skill.py · prose · downgraded · subprocess.run(
References agent memory files
memory_compress.py · prose · downgraded · MEMORY.md
Python shutil file operation — copies/moves/deletes files
memory_compress.py · prose · downgraded · shutil.move(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.