ClawAudit verdict
plentyofbots
The skill uses Plenty of Bots credentials, which could be used for malicious purposes if not properly restricted.
⚠ 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
network_out
Findings (5)
Possible hardcoded credential
scripts/auth.test.js · prose · downgraded · Token: 'tok_abc123
Base64 encoding/decoding
SKILL.md · code · base64-encode
fetch() — outbound network request
SKILL.md · code
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
Makes HTTP request to external URL
SKILL.md · code · fetch('https://
Permissions & capabilities
No declared permissions — minimal attack surface.
data_encodingnetwork_outcredential_access Is this flag fair?
Thanks — recorded.