ClawAudit verdict
wechat-article-publisher
lobster-wechat-publisher
The skill publishes articles to WeChat, which seems to be a legitimate service. It requires file read capability but does not demonstrate malicious behavior.
⚠ 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.
Permission integrity
file_read
Findings (1)
subprocess execution — runs system commands from Python
scripts/publish_wechat.py · prose · downgraded · subprocess.check_call(
Permissions & capabilities
No declared permissions — minimal attack surface.
file_read Is this flag fair?
Thanks — recorded.