tdd
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands such as
npm test,npm run typecheck, andnpm run lintto verify implementation success. - [PROMPT_INJECTION]: The skill uses high-pressure, imperative language like 'NO CODE WITHOUT A FAILING TEST FIRST', 'Delete means delete', and 'No exceptions' to override the agent's standard code-generation behavior and enforce a specific methodology.
- [PROMPT_INJECTION]: This skill presents an indirect prompt injection surface by converting untrusted user requirements into executable code and tests. 1. Ingestion points: Complex business logic and algorithm requirements provided by the user. 2. Boundary markers: The instructions lack explicit delimiters to isolate user-provided data from the agent's execution context. 3. Capability inventory: The agent possesses shell execution capabilities through npm scripts. 4. Sanitization: No validation or sanitization of user-provided data is mandated before it is used to generate code that is subsequently executed.
Audit Metadata