superpowers-test-driven-development

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional content and best practices for software development. It provides a structured workflow for writing tests before code.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use npm test to verify code changes. This is a standard and expected operation within a software development environment and does not involve arbitrary or malicious command injection.
  • [PROMPT_INJECTION]: The skill uses strong imperative language to define the TDD process (e.g., "Iron Law", "MANDATORY"). These are internal task constraints meant to guide the agent's coding behavior and do not attempt to bypass core safety guardrails or extract system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 08:18 AM