unit-test-generator

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a process for generating test suites from existing source code, which introduces a surface where malicious patterns in the input code could influence the agent's behavior during generation.\n
  • Ingestion points: Source code files (.ts, .tsx) are analyzed to create matching test structures.\n
  • Boundary markers: None mentioned; the instructions do not specify delimiting input code from generation logic.\n
  • Capability inventory: Examples include file system interaction (fs module) and mocking (vi.fn).\n
  • Sanitization: No sanitization logic is provided to handle potentially malicious comments or code structures in the source files.\n- [DYNAMIC_EXECUTION]: The skill includes a helper script that assembles executable code at runtime using string templates.\n
  • The generateTestTemplate function in scripts/generate-tests.ts constructs Vitest code blocks by interpolating file-derived strings into a template literal.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:14 PM