creating-claude-hooks

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [GENERAL] (SAFE): The content is purely instructional and provides guidance on hook development, including security best practices such as path sanitization and secret detection.
  • [DATA_EXPOSURE] (SAFE): The skill includes examples of how to block access to sensitive files (e.g., .env, .pem) and how to detect secrets in prompts within the user's developed hooks.
  • [REMOTE_CODE_EXECUTION] (SAFE): While the skill mentions external tools (prpm, jq) and links to a JSON schema on GitHub, it does not contain instructions to download and execute untrusted remote code automatically.
  • [COMMAND_EXECUTION] (SAFE): The chmod +x instructions are standard for the intended purpose of making user-created scripts executable and do not constitute an unauthorized privilege escalation risk within this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM