Caveat verdict

agentmail-integration

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

The skill provides a legitimate integration with AgentMail API for AI agent email automation. It does not contain any malicious code or intent.

⚠ 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.

50
security
60
transparency
70
maintenance

Findings (3)

Pattern match critical

Prompt injection — tries to override agent instructions

SKILL.md · code · ignore previous instructions

Pattern match medium

Python os.getenv — reads environment variable

SKILL.md · code · os.getenv(

Pattern match medium

References tunneling service

references/WEBHOOKS.md · code · ngrok

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_accessdata_encodingnetwork_in

Is this flag fair?

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