coverage
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes the application's source code and existing test files to identify coverage gaps, which creates a surface for indirect prompt injection from untrusted repository content.
- Ingestion points: The skill scans route definitions (Step 1), API route files, component files, and existing test scripts (e.g.,
*.spec.ts,*.spec.jsin Step 2). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing the content of these external files.
- Capability inventory: The skill can trigger test generation via the
/pw:generatecommand (Step 6) and recommends using files from atemplates/directory. - Sanitization: No sanitization or validation of the retrieved code content is mentioned before it is processed by the agent to create the coverage matrix or test plan.
Audit Metadata