skills/amit-t/skills/setup-pre-commit/Gen Agent Trust Hub

setup-pre-commit

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes system commands via the detected package manager (npm, pnpm, yarn, or bun) to install devDependencies and run tool initialization commands such as npx husky init and npx lint-staged.
  • [EXTERNAL_DOWNLOADS]: Fetches standard development dependencies including husky, lint-staged, and prettier from the npm registry. These are well-known, widely used tools for managing Git hooks and code formatting in JavaScript/TypeScript projects.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes local project data which creates a surface for indirect instructions, though the risk is localized to the repository context.
  • Ingestion points: Reads the project's package.json file to detect the presence of typecheck and test scripts (SKILL.md).
  • Boundary markers: Absent; the agent is instructed to read the file content directly to adapt the Husky hook configuration.
  • Capability inventory: Package installation, writing configuration files (.husky/pre-commit, .lintstagedrc, .prettierrc), npx execution, and git commit operations.
  • Sanitization: Absent; the skill does not specify validation or sanitization for the script names extracted from package.json before interpolating them into the generated .husky/pre-commit file.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 04:28 PM