ClawAudit verdict
yzj-form-parser
The skill is designed to parse and prerequisites - User has already logged into four platforms (Twitter, Weibo, Xiaohongshu, Wechat Official Account) - User has installed Hermes agent ## Usage ### Step 1: Generate draft ```bash openclaw zeelin-social-autopublisher generate --topic "AI" ``` ## Step 2: Dry-run ```bash openclaw zeelin-social-autopublisher dry-run --platforms twitter,weibo,xhs,wechat --content-out /tmp/zeelin.json ``` ## Step 3: Publish ```bash openclaw zeelin-social-autopublisher publish --platforms twitter,weibo,xhs,wechat --content-out /tmp/zeelin.json ``` ## Step 4: Report ```bash openclaw zeelin-social-autopublisher report --platforms twitter,weibo,xhs,wechat ```
⚠ 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+write
Permissions & capabilities
No declared permissions — minimal attack surface.
file_write Is this flag fair?
Thanks — recorded.