playwright-generate-test
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to generate and subsequently execute TypeScript code using the '@playwright/test' package. This functionality is the primary purpose of the skill and is handled via the Playwright MCP.
- [PROMPT_INJECTION]: The skill processes user-defined scenarios to generate code, representing an indirect prompt injection surface. 1. Ingestion points: User-provided scenarios. 2. Boundary markers: Absent from the instruction set. 3. Capability inventory: File system write access to the 'tests' directory and execution of generated tests. 4. Sanitization: Absent; the skill relies on the model's inherent safety training for code generation.
Audit Metadata