test-driven-development
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains instructional content and best practices for the Test-Driven Development (TDD) methodology. It does not contain malicious code, hidden instructions, or exfiltration patterns.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute standard development commands such as
npm testto verify software behavior. These are routine operations for a developer-oriented agent. - [INDIRECT_PROMPT_INJECTION]: The skill describes how an agent should process code and test files, establishing an attack surface for indirect prompt injection from user-provided files. Evidence chain:
- Ingestion points: Agent reads implementation and test code files from the local environment.
- Boundary markers: None explicitly defined to distinguish between user data and system instructions.
- Capability inventory: Shell execution capabilities for running test suites.
- Sanitization: None present in the skill instructions.
- Note: This represents an inherent risk in coding assistants rather than a specific malicious instruction in this skill.
Audit Metadata