test-coverage-improver
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes existing source code to identify coverage gaps and generate new tests. This process ingests untrusted source code as data, which is an attack surface for instructions hidden in code comments or metadata.
- Ingestion points: The agent reads existing source code and test files during the analysis phase.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between code-as-data and instructions.
- Capability inventory: The skill uses shell commands (npx jest, npx vitest) and file system operations to write new test files.
- Sanitization: No sanitization or validation of the ingested source code is performed before generating output.
- [DYNAMIC_EXECUTION]: The skill generates and writes executable TypeScript and JavaScript code (tests) to the file system based on the provided templates and the analyzed source code.
Audit Metadata