ClawAudit verdict
mentor
Skill scrapes public social media profiles (Weibo, Bilibili, Douyin) via ManoBrowser to build AI personas of real public figures; while data is described as public, automated bulk scraping of third-party platforms raises legal/ToS concerns and the data collection scope is broad.
⚠ 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)
HTTP request to bare IP address — common in malicious payloads
guides/VIDEO_SUBTITLE.md · code · http://127.0.0.1
subprocess execution — runs system commands from Python
scripts/bilibili_subtitle_batch.py · prose · downgraded · subprocess.run(
Uses XMLHttpRequest — network access
xiaohongshu-deep-profile-collect/SKILL.md · code · XMLHttpRequest
Makes HTTP request to external URL
bilibili-deep-profile-collect/SKILL.md · code · fetch(
'https://
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.