test-driven-development
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (specifically
npm test) during the Red and Green phases of the TDD cycle to verify test results. This is expected behavior for the stated purpose. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user data (feature requests and bug descriptions) and uses it to drive code generation and execution.
- Ingestion points: User-provided feature specifications and bug reports.
- Boundary markers: Absent; the skill does not provide delimiters or instructions to ignore embedded commands in user-provided data.
- Capability inventory: The skill requires the ability to write files (tests and implementation code) and execute shell commands (
npm test) within the user's environment. - Sanitization: Absent; user requirements are not sanitized or validated before being acted upon by the agent.
Audit Metadata