ClawAudit verdict
huo15-xiaohongshu
The skill's content includes an execution sink and provides features for generating and analyzing content on Xiaohongshu, which could be used for malicious purposes.
⚠ 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 (8)
References agent configuration files
CLAUDE.md · code · CLAUDE.md
References child_process — can spawn system processes
docs/changelog.md · prose · downgraded · child_process
subprocess execution — runs system commands from Python
scripts/assistant.py · prose · downgraded · subprocess.call(
Opens WebSocket connection
docs/changelog.md · prose · downgraded · WebSocket
Python urllib.request — network access
scripts/browser_bridge.py · prose · downgraded · urllib.request
Python shutil file operation — copies/moves/deletes files
scripts/coach_iterate.py · prose · downgraded · shutil.copy(
Python os.environ.get — reads environment variable
scripts/coin_word.py · prose · downgraded · os.environ.get(
Blob URL — may embed executable content
scripts/topic_ideas.py · prose · downgraded · blob:
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.