e2e
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill executes commands like 'yarn playwright test' and other scripts defined in 'package.json'. This behavior is the primary intended function of the skill for running tests in a development environment.
- [PROMPT_INJECTION] (LOW): The skill processes project-specific files like 'package.json' and '*.spec.md' which could contain instructions intended to influence the agent. 1. Ingestion points: package.json (scripts), *.spec.ts (test code), *.spec.md (requirements). 2. Boundary markers: Absent. 3. Capability inventory: Execution of shell commands via yarn and local file system modifications. 4. Sanitization: None implemented.
Audit Metadata