sendgrid
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides standard integration patterns for a well-known service (SendGrid).
- [CREDENTIALS_UNSAFE]: The skill correctly demonstrates using
process.env.SENDGRID_API_KEYrather than hardcoding credentials. No actual secrets were found. - [EXTERNAL_DOWNLOADS]: The skill recommends installing official, well-known packages (
@sendgrid/mailfrom NPM andsendgridfrom PyPI) which are standard for this integration. - [INDIRECT_PROMPT_INJECTION]: While the skill processes external webhook data (Category 8), it is for the purpose of updating database records (e.g., marking bounces) and does not involve re-evaluating that data as instructions for the agent, presenting a standard and safe implementation pattern.
Audit Metadata