coverage
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill maps the application surface by reading source code files and test specifications, creating a potential surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Scans local route definitions, component source code, API controller files, and test files (*.spec.ts/js) in the repository.
- Boundary markers: No specific delimiters or safety instructions are defined to separate the content of analyzed files from the agent's execution logic.
- Capability inventory: The skill uses an exploration subagent to crawl the codebase and can invoke a test generation command (/pw:generate).
- Sanitization: The skill does not explicitly describe any sanitization or validation of the data read from the local filesystem before it is processed by the AI.
Audit Metadata