hooks

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [Command Execution] (SAFE): The skill provides templates for shell wrappers and hook registration as part of its primary purpose.
  • [Unverifiable Dependencies & Remote Code Execution] (LOW): The documentation suggests using npx tsx, which downloads and executes external packages from the npm registry.
  • [Indirect Prompt Injection] (LOW): The hook handler pattern reads from stdin, creating an entry point for untrusted data. 1. Ingestion points: readStdin() in handler.ts. 2. Boundary markers: None present in template. 3. Capability inventory: Command execution via shell wrappers. 4. Sanitization: None present in template.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:56 PM