ClawAudit verdict
do-it
do-it-gungun
The skill's behavior seems ambiguous, as it mentions using '滚滚知识库作为决策依据' but doesn't provide clear details on how it works.
⚠ 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 (3)
Popular HTTP library — network access
PRODUCT-DESIGN.md · code · Axios
subprocess execution — runs system commands from Python
scripts/crawl_all.py · prose · downgraded · subprocess.run(
POSTs data to external URL
scripts/test_api.py · prose · downgraded · .post(
'http://
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.