add-product-e2e-eval
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard project-specific commands via
pnpmfor testing and validation purposes. These operations are transparent and limited to the local development environment. - [DATA_EXFILTRATION]: The instructions provide explicit safety measures to avoid data exposure. They mandate that credentials, secrets, and raw traces be excluded from logs, screenshots, and shared catalog data.
- [INDIRECT_PROMPT_INJECTION]: While the skill involves reading external project documentation which could technically serve as an injection surface, it includes instructions for sanitizing evidence and follows a highly structured workflow that limits the impact of untrusted data.
Audit Metadata