developing-genkit-js

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the genkit CLI, npm, and npx to perform common development operations, including environment setup, running application flows, and launching the developer UI.
  • [EXTERNAL_DOWNLOADS]: Fetches and installs the genkit-cli and official @genkit-ai plugin packages from the NPM registry as part of the setup and execution workflow.
  • [PROMPT_INJECTION]: The instructions include strong directives ('Do Not Trust Internal Knowledge', 'protocol is non-negotiable') intended to steer the agent's behavior toward the provided reference files and CLI documentation over its internal training. It also includes an indirect injection surface by reading local project configuration files.
  • Ingestion points: package.json (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Shell command execution (genkit start), file system writes (setup.md).
  • Sanitization: Not explicitly implemented in the provided logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 06:41 PM
Security Audit — agent-trust-hub — developing-genkit-js