resend-email

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documents methods for retrieving email lists from the Resend API, creating a channel for untrusted external data to enter the agent's context.
  • Ingestion points: SKILL.md describes listing emails via the https://api.resend.com/emails endpoint.
  • Boundary markers: The instructions do not specify any delimiters or instructions for the agent to disregard potential commands embedded within retrieved email bodies or subjects.
  • Capability inventory: The skill enables network operations via curl, Go's net/smtp package, and standard HTTP requests for email management.
  • Sanitization: No data sanitization or validation logic is provided for the fetched email content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:06 PM