Caveat verdict
study-buddy-niu
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
A study assistant for Japanese N2 and software architecture exams that records wrong answers to a Feishu Bitable; no capabilities declared and all behavior is purely educational with no concerning patterns.
⚠ 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.
70
security
80
transparency
80
maintenance
Findings (1)
Pattern match critical
Possible hardcoded credential
SKILL.md · code · TOKEN: "SoZ5bkTBOa3LQisZHO1cAQuknDh
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.