inbound-processing
Warn
Audited by Snyk on Apr 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: 0.90). The SKILL.md explicitly ingests untrusted, user-generated inbound email via provider webhooks (Postmark/SendGrid/Mailgun/SES) and instructs the agent to parse, classify, and route/auto-respond on that content (see "Provider inbound features", webhook processing, and "Prompt injection detection"), so third‑party emails can directly influence agent decisions and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata