test-driven-development

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The instructions direct the agent to run npm test to verify the state of the codebase during the TDD process. This is standard behavior for a development-focused skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves reading user-provided code and executing tests against it. While this involves processing untrusted data, the risk is inherent to the primary purpose of a code-testing skill and is handled within the scope of a development environment.
  • Ingestion points: Reads existing source code and test files.
  • Boundary markers: None explicitly defined in the skill instructions.
  • Capability inventory: Executes shell commands (npm test) and performs file system operations (write/delete).
  • Sanitization: Relies on the user's test runner environment.
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill focuses on promoting software engineering best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:05 PM
Security Audit — agent-trust-hub — test-driven-development