Caveat verdict
superhero
45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.
The skill provides access to blockchain operations, which could be used maliciously.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
90
security
70
transparency
80
maintenance
Findings (1)
Pattern match medium
Social engineering — falsely claims user authorization
skill-card.md · prose · downgraded · the user has configured
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.