agentmail

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow consumes incoming emails from an external email service where outsiders can send messages.

HIGH W008: Secret detected in skill content (API keys, tokens, passwords).

• Secret detected (high risk: 1.00). An active, high-entropy API key belonging to AgentMail is hardcoded in the documentation (references/agentmail-setup-log.md line 11). The string am_us_7bd6831fbba7c6996f0c60bce223865babf26d147747044befea0c5fc68374f1 uses a specific vendor prefix (am_us_) and is a full 64-character hex-encoded secret token, not a placeholder.