test-driven-development
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-provided feature descriptions, bug reports, and existing code segments.
- Ingestion points: Task requirements for new features, bug fixes, and refactoring mentioned in SKILL.md.
- Boundary markers: The skill lacks explicit instructions or delimiters to isolate user-supplied content from the agent's control logic.
- Capability inventory: The skill directs the agent to execute shell commands (
npm test) and perform destructive file system operations (deleting code) in SKILL.md. - Sanitization: No validation or sanitization of input code or file paths is specified.
- [COMMAND_EXECUTION]: The instructions mandate the execution of
npm testto verify code state. While standard for development, this involves shell command execution within the project environment. - [PROMPT_INJECTION]: The skill utilizes highly assertive and imperative language—such as 'The Iron Law', 'MANDATORY. Never skip', and 'Delete means delete'—to strictly constrain the agent's behavior. These instructions could cause the agent to override user intent or delete existing production code if it deems the TDD process was not correctly followed.
Audit Metadata