ClawAudit verdict
wechat-copywriter
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
The skill seems to be a simple text generation tool for WeChat and does not contain any obvious risks.
⚠ 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.
95
security
60
transparency
50
maintenance
Findings (2)
Pattern match low
Node http/https module — low-level network access
generate.js · prose · downgraded · require('https')
Pattern match low
Accesses sensitive environment variables
generate.js · prose · downgraded · process.env.DEEPSEEK_API_KEY
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.