agentmail

Warn

Audited by Snyk on Mar 8, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). This skill ingests untrusted, user-generated content via incoming email webhooks (see SKILL.md and references/WEBHOOKS.md handling of "message.received" events and the webhook receiver examples), and the examples show the agent parsing email subject/body/attachments and taking actions (auto-replies, creating tasks, creating GitHub issues), so third-party content can directly influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 11:37 PM