ClawAudit verdict
cli-anything-openclaw
The skill adapts CLI-Anything for OpenClaw workflows, potentially involving code execution.
⚠ 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)
subprocess execution — runs system commands from Python
references/harness.md · code · subprocess.run(
Instructs covert action — may act without user awareness
references/harness.md · prose · downgraded · silently
Python os.environ.get — reads environment variable
references/harness.md · prose · downgraded · os.environ.get(
Opens WebSocket connection
references/harness.md · prose · downgraded · websocket
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/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.