resend
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill uses authoritative directives ("CRITICAL", "MUST", "Do not proceed") to instruct the agent to prioritize external documentation over its internal training data. This pattern attempts to override the model's internal knowledge state in favor of remote content.
- [INDIRECT_PROMPT_INJECTION]: \n
- Ingestion points: The agent is directed to fetch and process content from
https://resend.com/docs/llms.txtusingWebFetch(SKILL.md). \n - Boundary markers: The instructions do not define clear boundaries or specify that the agent should ignore instructions embedded within the fetched document. \n
- Capability inventory: The skill facilitates code generation and API integration tasks, which may involve executing commands or managing secrets in the user's environment. \n
- Sanitization: There are no instructions for the agent to sanitize or validate the content of the remote documentation file before use.
- [EXTERNAL_DOWNLOADS]: Fetches live documentation from Resend's official domain (
https://resend.com/docs/llms.txt) to provide up-to-date API information.
Audit Metadata