agentmail

Warn

Audited by Snyk on Jul 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). SKILL.md describes webhook-driven processing where incoming email content (outsider-authored messages) is placed into the agent context via the webhook transform’s text: ... ${payload.message.subject} ... ${payload.message.text} path.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 10, 2026, 03:05 PM
Issues
1
Security Audit — snyk — agentmail