setup-pre-commit

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands via the repository's package manager (npm, pnpm, yarn, or bun) to install development dependencies and initialize tools (e.g., npx husky init). These operations are necessary for the skill's primary function of setting up the development environment.
  • [PERSISTENCE]: The skill creates a git pre-commit hook in the .husky/ directory and modifies the package.json prepare script. While these mechanisms ensure code execution in future sessions (every commit), they are standard industry practices for the tools being configured and are the explicit purpose of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill parses local repository configuration files to determine the environment and adapt its instructions. This involves processing untrusted data from the filesystem.
  • Ingestion points: Reads package.json and lock files (package-lock.json, pnpm-lock.yaml, yarn.lock, bun.lockb) to detect package managers and existing scripts.
  • Boundary markers: None present in the instructions.
  • Capability inventory: Writing configuration files, installing packages, and executing shell commands through Husky initialization.
  • Sanitization: No explicit sanitization of repository content is performed before logic branching.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 09:28 AM