ClawAudit verdict
wechat-publisher-skill-clean
Simplified wechat-publisher variant that auto-publishes AI news digests to WeChat draft box using user-configured credentials with the official WeChat API.
⚠ 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)
References sudo — requests elevated privileges
docs/user_guide.md · code · sudo
apt-get install — installs system packages
docs/user_guide.md · code · apt-get install
Possible hardcoded credential
scripts/news_collector.py · prose · downgraded · apiKey=",
Python os.environ.get — reads environment variable
scripts/publish.py · prose · downgraded · os.environ.get(
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.