resend
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [REMOTE_CODE_EXECUTION]: No unauthorized remote code execution patterns were detected. The skill uses standard package management (npm/npx) to run its own scripts and depends on official Zapier SDKs.
- [DATA_EXFILTRATION]: Network activity is restricted to the legitimate Resend API domain (api.resend.com). No patterns of credential harvesting or unauthorized data transmission to third-party domains were found.
- [CREDENTIALS_UNSAFE]: The skill correctly avoids hardcoding secrets. It uses standard environment variable resolvers (re_... keys) and Zapier's managed authentication platform, following industry-standard secret management practices.
- [COMMAND_EXECUTION]: The entry point cli.js performs a runtime readiness check and spawns the skill's TypeScript or compiled JavaScript source in a subprocess. This is a controlled execution of the skill's internal logic and does not expose the system to arbitrary command injection.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect injection via data ingested through tool inputs in scripts/*.ts. However, SKILL.md defines boundary markers via explicit disambiguation instructions for the agent. The capability inventory is restricted to HTTP requests to api.resend.com. Input sanitization is enforced by Zod schemas for all tool parameters.
Audit Metadata