gemini-api-dev

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch API discovery specifications and documentation index files (llms.txt) from official Google domains, specifically generativelanguage.googleapis.com and ai.google.dev. These are recognized as well-known and trusted services.
  • [COMMAND_EXECUTION]: The documentation mentions the installation of official Google SDKs (google-genai, @google/genai, and google.golang.org/genai) via standard package managers like pip, npm, and go. These are legitimate development operations involving official vendor libraries.
  • [PROMPT_INJECTION]: The content includes instructions regarding model deprecation and versioning (e.g., claiming certain models are legacy and that the agent's internal knowledge may be outdated). While these are directives to the agent, they are technical in nature and remain within the scope of providing API documentation rather than attempting to bypass safety protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 08:36 PM
Security Audit — agent-trust-hub — gemini-api-dev