gemini
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
geminicommand to interact with the Google Gemini service. This behavior is expected and limited to the tool's intended functionality without privilege escalation. - [EXTERNAL_DOWNLOADS]: The skill installs the
gemini-clitool via Homebrew, which is a well-known and trusted package management service. The source is consistent with the tool's intended use-case. - [PROMPT_INJECTION]: The skill processes user input as prompts for the Gemini model. While this creates an indirect prompt injection surface common to LLM interfaces, the skill contains no malicious instructions or bypass attempts itself, and this functionality is core to its primary purpose.
Audit Metadata