ClawAudit verdict
cyber-security-engineer
fletcher-cyber-security-engineer
The skill implements least-privilege security controls, approval gates, and compliance reporting — all capabilities directly serve the stated security-hardening purpose with no evidence of malicious behavior.
⚠ 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 (5)
References sudo — requests elevated privileges
references/least-privilege-policy.md · prose · downgraded · sudo
subprocess execution — runs system commands from Python
scripts/egress_monitor.py · prose · downgraded · subprocess.run(
Accesses OpenClaw config/secrets directly
scripts/live_assessment.py · prose · downgraded · ~/.openclaw/openclaw.json
Python os.environ.get — reads environment variable
scripts/guarded_privileged_exec.py · prose · downgraded · os.environ.get(
Sets world-executable permissions
scripts/install-openclaw-runtime-hook.sh · prose · downgraded · chmod 700
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.