skills/terminalskills/skills/husky/Gen Agent Trust Hub

husky

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions utilize standard shell commands for installing and initializing development tools within a local environment, such as npm install and npx husky init.- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where repository files are automatically processed by tools, creating a standard surface area for indirect prompt injection.
  • Ingestion points: Staged repository files (referenced in SKILL.md).
  • Boundary markers: None explicitly defined in the hook scripts or configuration.
  • Capability inventory: Executes eslint, prettier, and npm test across repository files via Git hooks defined in SKILL.md.
  • Sanitization: None; the skill relies on the internal security of the configured linters and test runners.- [SAFE]: The external dependencies (husky, lint-staged) are widely-used, industry-standard packages for Git hook management and code formatting. The instructions follow standard integration practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 06:11 PM
Security Audit — agent-trust-hub — husky