ClawAudit verdict
ly-wechat-publisher
The skill has no obvious malicious behavior but its extensive use of system capabilities could be considered a risk.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (3)
References sudo โ requests elevated privileges
docs/user_guide.md ยท code ยท sudo
apt-get install โ installs system packages
docs/user_guide.md ยท code ยท apt-get install
Python os.environ.get โ reads environment variable
scripts/publish.py ยท prose ยท downgraded ยท os.environ.get(
Permissions & capabilities
No declared permissions โ minimal attack surface.
Is this flag fair?
Thanks โ recorded.