resend
Warn
Audited by Snyk on Feb 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: 0.90). The skill explicitly ingests user-generated emails and attachments via the Resend inbound webhook (email.received) and then calls resend.emails.receiving.get and downloads attachment.download_url to retrieve content which is then forwarded to the AI agent for processing, exposing the agent to untrusted third‑party content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill fetches inbound email bodies at runtime from the Resend API (e.g., https://api.resend.com/emails) and then forwards that content into agent.processEmail, meaning externally-sent email content can directly control the agent's prompts/instructions.
Audit Metadata