skills/jezweb/claude-skills/vitest/Gen Agent Trust Hub

vitest

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes data from local project files to automate configuration.\n
  • Ingestion points: Reads project files such as package.json, tsconfig.json, and wrangler.toml to detect project types and dependencies.\n
  • Boundary markers: The skill does not implement explicit delimiters or safety instructions when processing data from these external files.\n
  • Capability inventory: The skill manages dependencies via shell commands (pnpm) and writes configuration and sample test files to the workspace.\n
  • Sanitization: No specific validation or sanitization of strings extracted from project metadata is described before their use in commands or file templates.\n- [COMMAND_EXECUTION]: The skill executes shell commands to perform package management and verify the test setup.\n
  • Evidence: Orchestrates commands like 'pnpm add', 'pnpm remove', and 'pnpm test:run' to configure the development environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:22 AM
Security Audit — agent-trust-hub — vitest