agent-email-inbox

Warn

Audited by Snyk on Apr 16, 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). The skill explicitly fetches and ingests inbound email bodies from external senders via resend.emails.receiving.get in the webhook flow (see "Webhook Endpoint" in SKILL.md), then passes that untrusted, user-generated email content to agent.processEmail, meaning third-party emails can directly influence agent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 16, 2026, 02:34 PM
Issues
1