genkit
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as an architectural assistant for Genkit workflows. It utilizes a structured reasoning process to help developers decide between server-side Genkit implementations, client-side SDK usage, or standard route handlers.
- [EXTERNAL_DOWNLOADS]: The skill provides links to official documentation on
firebase.google.comandgenkit.dev. These references are to well-known technology services and are used to provide legitimate technical context. - [PROMPT_INJECTION]: The instructions include logical checks to ensure the agent remains within the scope of Genkit development and avoids misinterpreting user requests for adjacent tools like the Firebase CLI or client-side SDKs. No adversarial or bypass patterns were found.
- [COMMAND_EXECUTION]: The skill's allowed tools (Bash, Write, etc.) are standard for development agents. No scripts, automated command execution, or dangerous command patterns were detected in the files.
- [DATA_EXFILTRATION]: The analysis found no hardcoded secrets, access to sensitive local paths, or network exfiltration patterns. All documented behaviors are consistent with its purpose as a technical design guide.
Audit Metadata