genkit
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install official framework packages from the NPM registry.
- Evidence: Installation commands for
genkit-cli,genkit, and@genkit-ai/google-genaiare provided inSKILL.md. - [COMMAND_EXECUTION]: The skill utilizes official CLI tools and local script execution for development and workflow management.
- Evidence: Instructions include running
genkit start,genkit flow:run, andgenkit eval:flow. - Evidence: Uses
npx tsxto execute local TypeScript code, which is the standard runtime pattern for the framework. - [PROMPT_INJECTION]: The skill facilitates building workflows that ingest untrusted user input, presenting a surface for indirect prompt injection (Category 8).
- Ingestion points: User data enters the AI flows through the input parameters in
genkit flow:run(documented inSKILL.md). - Boundary markers: None explicitly defined in the provided command examples.
- Capability inventory: The skill has access to
BashandWritetools to interact with the environment. - Sanitization: No specific input sanitization or validation guidelines are included in the instructions for the generated flows.
Audit Metadata