review
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted test files (*.spec.ts, *.spec.js) and configuration files (playwright.config.ts) to identify anti-patterns.
- Ingestion points: Test files and project configuration files are read into the agent's context in Step 1 and Step 2.
- Boundary markers: Absent. The instructions do not define delimiters for the ingested code or provide guidance to the agent to ignore instructions that might be embedded within comments or strings in the code files.
- Capability inventory: The skill utilizes the
Edittool to apply fixes to the codebase and mentions the ability to spawn sub-agents for parallel processing. - Sanitization: Absent. Content from external files is evaluated directly for patterns without escaping or sanitization to prevent the agent from interpreting the code as instructions.
Audit Metadata