agentmail

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows fetching and processing emails from third-party providers (e.g., "Integrate agentmail with email services like Gmail or Outlook" and CLI/API examples that "Fetch an email" and call /classify and /draft), so the agent ingests untrusted, user-generated email content that can directly influence classification, drafting, scheduling, and subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 10:46 PM