email

Warn

Audited by Snyk on May 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: 0.80). The SKILL.md explicitly instructs the agent to "receive verification emails" and to "Read inbox" via the agentmail REST/CLI endpoints (e.g., GET /v0/inboxes/$AGENTMAIL_EMAIL/messages and threads), meaning the agent will fetch and interpret untrusted, user-generated email content that can contain actionable instructions (verification links or replies) which may influence subsequent tool use and decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 10, 2026, 06:50 PM
Issues
1