ClawAudit verdict
yuqing-push-skill
The skill pushes formatted content to a specified group robot Webhook and does not exfiltrate data or execute remote code.
⚠ 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 (3)
Uses eval() — can execute arbitrary code
push_skill.py · prose · downgraded · eval(
References webhook/callback URL
SKILL.md · prose · downgraded · webhook_url
Python os.getenv — reads environment variable
push_skill.py · prose · downgraded · os.getenv(
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.