developing-genkit-js
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a detailed documentation set for the Genkit framework. No malicious patterns, such as prompt injection for jailbreaking or unauthorized data exfiltration, were identified during the analysis.
- [EXTERNAL_DOWNLOADS]: The skill references several official packages, including 'genkit-cli' and various '@genkit-ai/*' libraries. These are official vendor resources and well-known development dependencies associated with the skill's author.
- [COMMAND_EXECUTION]: Instructions include standard development commands like 'npm install', 'genkit start', and 'npx tsx'. These are used appropriately to facilitate the setup and execution of the Genkit development environment.
- [PROMPT_INJECTION]: The skill uses instructional steering (e.g., 'Critical: Do Not Trust Internal Knowledge') to prioritize the provided documentation over potentially outdated pre-trained model knowledge. This is a common and legitimate pattern for technical guide skills and does not constitute a malicious attempt to bypass safety filters.
- [CREDENTIALS_SAFE]: The documentation explicitly recommends storing API keys in environment variables or '.env' files rather than hardcoding them, which is a standard security best practice.
Audit Metadata