skill-developer

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The documentation describes a hook-based architecture (UserPromptSubmit) that injects formatted context into the agent's prompt stream. This is a core architectural feature of the skill system being documented and includes visual boundary markers for clarity.
  • [DYNAMIC_EXECUTION]: Example commands for manual testing utilize 'npx tsx' to execute local TypeScript hook scripts, which is standard practice for the development workflows described.
  • [PRIVILEGE_ESCALATION]: Troubleshooting steps mention using 'chmod +x' to make local shell wrappers executable, representing standard administrative procedures for local script management.
  • [SAFE]: No obfuscation, persistence mechanisms, or credential harvesting patterns were found in the skill content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 04:35 PM
Security Audit — agent-trust-hub — skill-developer