ClawAudit verdict
openclaw-rpa
The skill enables browser automation but requires careful monitoring to ensure it aligns with user intentions.
⚠ 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
articles/python-snippet-design.md · prose · downgraded · | python
Uses exec() — may execute shell commands
articles/python-snippet-design.md · prose · downgraded · exec(
subprocess execution — runs system commands from Python
envcheck.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
articles/api-call-guide.md · prose · downgraded · os.environ.get(
Python shutil file operation — copies/moves/deletes files
rpa_manager.py · prose · downgraded · shutil.rmtree(
Python urllib.request — network access
rpa_manager.py · prose · downgraded · urllib.request
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.