test-detect

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local testing commands including npx, python -m pytest, go test, cargo test, mix test, and bundle exec rspec. This is the primary intended function of the skill.
  • [COMMAND_EXECUTION]: The skill interpolates user-provided file paths from arguments into shell commands to run specific tests. While this is a common pattern for CLI wrappers, it relies on the underlying agent environment to handle path sanitization.
  • [PROMPT_INJECTION]: The skill has an indirect injection surface in Step 5 where it reads and analyzes source code content to generate new test files. Instructions embedded in source code comments could potentially influence the test generation logic.
  • Ingestion points: Reads source files (e.g., src/utils.ts) via argument parsing.
  • Boundary markers: None explicitly defined in the skill instructions to separate code content from instructions.
  • Capability inventory: Executes subprocesses (npx, pytest, etc.) and performs file write operations to save generated tests.
  • Sanitization: No explicit sanitization or filtering of source code content is described before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 08:38 AM