setup-resend
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a template for handling incoming emails (
templates/inbound.ts), which introduces a surface for indirect prompt injection if the agent is instructed to act on the content of these emails. - Ingestion points: The
handleInboundRequestfunction receives webhook data and fetches the full email content usingresend.emails.receiving.get(emailId)intemplates/inbound.ts. - Boundary markers: The skill does not provide or mandate the use of delimiters or 'ignore' instructions for the processed email content.
- Capability inventory: The skill is designed for use-cases where 'inbound mail triggers actions', potentially allowing external senders to influence agent behavior.
- Sanitization: The provided templates lack sanitization or validation logic for email bodies or subjects beyond basic signature verification for the webhook itself.
- [SAFE]: The skill follows security best practices by recommending the use of
.env.localfor secrets (RESEND_API_KEY) and providing explicit warnings about the broad permissions required for inbound mail access.
Audit Metadata