Caveat verdict
broedkrumme-kalibr
45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.
The skill captures agent outcomes and LLM calls for continuous improvement, requiring an API key and tenant ID. Accessing credentials is a concern.
⚠ 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
40
transparency
60
maintenance
Findings (1)
Pattern match medium
Dynamic import() — loads module at runtime
index.ts · prose · downgraded · import("
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.