ClawAudit verdict
zentao-autoreport
The skill automates work hour reporting and does not exfiltrate data or execute remote code.
⚠ 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)
Pipe to python — executes piped content as Python code
scripts/match-tasks.sh · prose · downgraded · | python3
Python urllib.request — network access
scripts/match-tasks.py · prose · downgraded · urllib.request
Uses XMLHttpRequest — network access
scripts/match-tasks.py · prose · downgraded · XMLHttpRequest
Popular HTTP library — network access
scripts/match-tasks.py · prose · downgraded · Got
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.