ClawAudit verdict
Proactive Intelligence
proactive-intelligence
This skill combines proactive and self-improving features, adding automated skill upgrades and editing capabilities. It seems to follow standard rules for autonomous work and self-improvement.
⚠ 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.
Permission integrity
agent_memory
Findings (5)
Pipe to python — executes piped content as Python code
setup.md · prose · downgraded · | Python
References agent memory files
SKILL.md · code · memory.md
subprocess execution — runs system commands from Python
skill-manager.py · prose · downgraded · subprocess.run(
subprocess with shell=True — command injection vector
skill-manager.py · prose · downgraded · subprocess.run(
cmd,
shell=True
Python shutil file operation — copies/moves/deletes files
skill-evolver.py · prose · downgraded · shutil.copytree(
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.
agent_memory Is this flag fair?
Thanks — recorded.