Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK for enterprise AI applications. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./cli-tool/components/skills/ai-research/gemini-api-agent-platform/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow is SDK and API guidance from first-party Google documentation, but the optional Search Grounding and URL Context examples let the agent fetch arbitrary outsider-authored web pages, which is low exposure because the agent must actively trigger the fetch.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.