ClawAudit verdict
wechat-publisher-pro
Publishes Markdown or HTML articles to WeChat Official Account draft box using official APIs with user-supplied credentials via environment variables.
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 (2)
Possible hardcoded credential
SKILL.md ยท code ยท secret="ไฝ ็ APPSECRET
Pipe to python โ executes piped content as Python code
ACCURACY_POLICY.md ยท prose ยท downgraded ยท | Python
Permissions & capabilities
No declared permissions โ minimal attack surface.
Is this flag fair?
Thanks โ recorded.