resend
Warn
Audited by Snyk on Feb 23, 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's webhook-based inbound flow explicitly fetches and ingests arbitrary incoming emails via resend.emails.receiving.get (see agent-email-inbox and resend-inbound SKILL.md webhook examples) and then forwards email bodies to the AI agent (e.g., agent.processEmail / processWithAgent), meaning untrusted, user-generated email content is read and can influence agent actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly fetches email content at runtime from the Resend API (e.g., https://api.resend.com via resend.emails.receiving.get) and forwards that content into agent.processEmail, so externally-supplied email content can directly control the agent's prompts.
Audit Metadata