google-gemini-api
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install official Google GenAI SDKs and developer utilities from well-known registries like PyPI, npm, and Maven, as well as official GitHub organizations. These installation steps are standard for the Gemini development environment.
- [INDIRECT_PROMPT_INJECTION]: The skill describes capabilities such as Google Search grounding, URL context, and File Search that allow the agent to ingest content from the public web and uploaded documents. This creates an inherent vulnerability surface where untrusted data could influence agent behavior, though the documented API includes integrated safety filters to mitigate these risks.
Audit Metadata