skill-developer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Unverifiable Dependencies & Remote Code Execution] (INFO): The documentation describes the use of npx tsx for runtime script execution, which involves fetching packages from the npm registry. This is a standard development practice but represents an external dependency.
- [Dynamic Execution] (INFO): The framework architecture relies on executing shell scripts and TypeScript files at runtime to modify agent behavior. This is the intended design for providing hook-based extensibility.
- [Indirect Prompt Injection] (INFO): The system processes file content and injects data into the AI prompt context (via stdout and stderr). While no malicious intent is present in these files, this architecture requires careful sanitization of processed content to prevent injection.
- [Prompt Injection] (SAFE): No evidence of direct prompt injection or attempts to bypass safety filters were found in the provided documentation.
Audit Metadata