review
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external test files and project configurations, which creates an attack surface for indirect prompt injection where malicious natural language instructions hidden in code could override agent behavior.
- Ingestion points: The skill reads playwright.config.ts, *.spec.ts, *.spec.js, and related page object/fixture files during the initial context gathering phase.
- Boundary markers: There are no explicit delimiters or specific instructions for the agent to disregard embedded prompts or distinguish between code and natural language instructions.
- Capability inventory: The skill utilizes the Edit tool to apply automated fixes to code and has the ability to spawn sub-agents for parallel file processing.
- Sanitization: No sanitization, filtering, or validation is performed on the ingested source code content before it is evaluated by the agent.
Audit Metadata