ClawAudit verdict
maibei-upload-audit
The skill runs an upload and audit pipeline, which may involve executing scripts or commands that could potentially be exploited.
⚠ 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)
<script> tag in markdown — potential code injection
scripts/html_report.py · prose · downgraded · <script>
Possible hardcoded credential
scripts/run_workflow_curl_examples.sh · prose · downgraded · TOKEN="${TOKEN:-}
HTTP request to bare IP address — common in malicious payloads
scripts/share_url.py · prose · downgraded · http://127.0.0.1
Python urllib.request — network access
scripts/share_url.py · prose · downgraded · urllib.request
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.