writing-tests
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install standard development dependencies including
vitest,@testing-library/react, and@testing-library/jest-domfrom the official NPM registry. - [COMMAND_EXECUTION]: The skill uses standard shell commands to inspect configuration files (
cat package.json), manage dependencies, and execute the test runner (npm test). These are expected behaviors for a test-writing utility. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill reads local source code files to identify functions, components, and logic for test generation (Step 3).
- Boundary markers: The instructions do not explicitly define boundary markers or delimiters for the ingested code content.
- Capability inventory: The skill can create new test files on the filesystem and execute terminal commands to run the test suite.
- Sanitization: There is no specific mention of sanitization for the ingested code before analysis, representing a standard surface for indirect prompt injection common in code-analysis skills.
Audit Metadata