coverage
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted application source code and test files, creating a potential surface for instructions embedded in code comments or strings to influence the agent.
- Ingestion points: Route definitions, component logic, API controllers, and test files (*.spec.ts/js) referenced in the analysis steps.
- Boundary markers: No explicit delimiters are used to isolate ingested code content from agent instructions.
- Capability inventory: The skill utilizes the Explore subagent and the /pw:generate tool to analyze the project and create new files.
- Sanitization: The skill does not describe specific measures to filter or sanitize processed code content.
- [NO_CODE]: The skill consists solely of instructions and metadata without providing any external scripts or binary executables.
Audit Metadata