ClawAudit verdict

windows-rpa

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill automates interactions with desktop applications, which may lead to unintended interactions or security risks if not properly monitored.

⚠ 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.

80
security
100
transparency
90
maintenance

Findings (2)

Pattern match medium

subprocess with shell=True — command injection vector

rpa.py · prose · downgraded · subprocess.Popen(f'start "" "{app_path}" {args.args}', shell=True

Pattern match medium

subprocess execution — runs system commands from Python

rpa.py · prose · downgraded · subprocess.run(

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

Requires 1 system binary.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API