ClawAudit verdict
esr-openclaw-checklist
This skill runs a local Python security checklist script at a fixed path and displays its output unchanged to the user; it executes no remote code, accesses no credentials, and explicitly instructs the agent not to modify system config without user confirmation.
⚠ 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 (6)
Pipe to python — executes piped content as Python code
CRON_CONFIG.md · code · | python3
subprocess execution — runs system commands from Python
CRON_CONFIG.md · code · subprocess.run(
Accesses OpenClaw config/secrets directly
USAGE_GUIDE.md · code · ~/.openclaw/openclaw.json
subprocess with shell=True — command injection vector
scripts/openclaw_checklist.py · prose · downgraded · subprocess.check_output(cmd, shell=True
HTTP request to bare IP address — common in malicious payloads
scripts/openclaw_checklist.py · prose · downgraded · http://127.0.0.1
References tunneling service
scripts/openclaw_checklist.py · prose · downgraded · ngrok
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.