test-driven-development

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No evidence of credential theft, data exfiltration, or unauthorized persistence was found. The skill adheres to standard software development practices.
  • [Indirect Prompt Injection] (LOW): The skill possesses an ingestion surface for untrusted data as it processes user requirements to generate and execute code/tests.
  • Ingestion points: User instructions for features and bugfixes are interpolated into code generation prompts.
  • Boundary markers: Absent. The skill does not explicitly define delimiters for user-provided requirements.
  • Capability inventory: The skill uses npm test to execute generated code, which could potentially run malicious code if the user-provided requirements contain an injection attack targeting the test environment.
  • Sanitization: Absent. The skill does not describe methods for sanitizing user input before generating executable tests.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:48 PM