Caveat verdict

nano-gpt-plugin

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Plugin descriptor with no executable content; describes a NanoGPT provider integration with standard auth and usage tracking — behavior matches stated purpose.

⚠ 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.

48
security
70
transparency
60
maintenance

Findings (3)

Pattern match critical

Possible hardcoded credential

PLAN.md · code · apiKey: "test-key

Pattern match high

Recursive delete from root or home — destructive command

final_integration_test.sh · prose · downgraded · rm -rf /

Pattern match low

Makes HTTP request to external URL

docs/05-openclaw-provider-sdk.md · code · fetch(`https://

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API