test-driven-development

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute npm test to verify software behavior throughout the development process. This is a standard and expected part of the professional development workflow described.
  • [PROMPT_INJECTION]: The skill establishes an Indirect Prompt Injection surface by directing the agent to execute tests on code generated from user-provided requirements. This creates a potential vector where a malicious requirement could result in the execution of unsafe code during the test phase.
  • Ingestion points: User-provided feature descriptions and bug reports (implicitly used to generate tests and code).
  • Boundary markers: The instructions do not define specific delimiters or isolation markers for user-provided input.
  • Capability inventory: The workflow involves shell execution via npm test to run generated test suites.
  • Sanitization: The skill does not provide explicit sanitization or validation logic for user requirements before they are used to generate executable tests.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 09:09 PM