setup-pre-commit

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the local package manager (npm, pnpm, yarn, or bun) to install devDependencies and executes npx husky init to configure the Husky environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the repository's package.json to detect existing scripts (typecheck, test) and lock files. While this is a data ingestion surface, it is used solely to adapt the configuration to the specific project context.
  • Ingestion points: Reads package.json and project root for lock files (SKILL.md).
  • Boundary markers: None used when reading file contents.
  • Capability inventory: Uses npx, npm/yarn/pnpm/bun for installation and execution; performs file writes for configuration files.
  • Sanitization: None; script names are used as found in the manifest.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:51 PM
Security Audit — agent-trust-hub — setup-pre-commit