test-driven-development

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill instructs the agent to execute standard test commands (e.g., npm test) to verify functionality. This is the intended purpose of a TDD skill and is conducted in a developer-expected context.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) because it ingests untrusted user requirements to generate and subsequently execute code. Evidence:
  • Ingestion points: User-provided feature specifications and bug reports used to drive the TDD cycle in SKILL.md.
  • Boundary markers: The instructions rely on markdown blocks but do not provide explicit delimiters or instructions to ignore embedded prompts in user-provided code requirements.
  • Capability inventory: The agent executes generated code through command-line test runners (npm test) and dispatches work to external agent skills (code-simplifier).
  • Sanitization: No validation or sanitization is performed on user requirements before they are used to generate tests and implementation code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:50 PM