gemini-api-dev

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill includes directives designed to override the agent's internal knowledge. It explicitly states, "Your knowledge is outdated," and instructs the agent to treat established model versions (1.5, 2.0, 2.5) as legacy in favor of specific new identifiers (gemini-3-*).
  • [EXTERNAL_DOWNLOADS]: The instructions direct the user to install several SDKs, including 'google-genai' for Python and '@google/genai' for Node.js. These are official packages from a well-known service provider.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:49 PM
Security Audit — agent-trust-hub — gemini-api-dev