koa-typescript
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION] (SAFE): The skill uses persona-setting language ('You are an expert...') to define the agent's role but does not contain any patterns aimed at bypassing safety filters or overriding system instructions.
- [CREDENTIALS_UNSAFE] (SAFE): No hardcoded credentials were found. The skill explicitly recommends using environment variables for secrets (JWT_SECRET) and warns against committing secrets to version control.
- [EXTERNAL_DOWNLOADS] (SAFE): The documentation and code snippets reference standard, well-maintained libraries from the Node.js ecosystem (e.g., Koa, Zod, Helmet).
- [DATA_EXFILTRATION] (SAFE): No unauthorized data access or network transmission patterns were detected. Network-related code is limited to standard middleware configuration.
Audit Metadata