building-stories-with-tdd
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows established development patterns for NestJS and Playwright. It emphasizes security reviews, input validation, and proper authorization decorators (@Roles, @Restricted) as part of the development lifecycle.
- [DYNAMIC_EXECUTION]: The skill generates and executes code as part of its core TDD functionality. It uses standard tools like Vitest and Playwright to run tests in an isolated environment (local test database).
- [COMMAND_EXECUTION]: It utilizes project-local CLI tools and package manager commands (pnpm, lt-cli) to manage the development environment, which is standard for developer-focused agent skills.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes untrusted user requirements, it provides clear instructions for the agent to clarify ambiguities and validate inputs, reducing the risk of malicious instructions within stories.
Audit Metadata