coverage
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local project environment, such as source code, route definitions, and existing test specifications, which serves as a potential surface for indirect injection.
- Ingestion points: Scanning of
*.spec.ts,*.spec.js, and application route/API definitions inSKILL.md. - Boundary markers: The instructions do not define clear delimiters or "ignore instructions" warnings when processing the contents of these files.
- Capability inventory: The skill uses analysis results to suggest test plans and can invoke the
/pw:generatetool to create new files. - Sanitization: There is no mention of sanitizing or escaping content extracted from project files before it is interpolated into the agent's context or tool parameters.
- [COMMAND_EXECUTION]: The skill includes a step to auto-generate code by invoking the
/pw:generatetool. This is a functional feature for test creation but involves executing commands based on the analysis of external files.
Audit Metadata