gemini
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill metadata specifies the installation of 'gemini-cli' via Homebrew ('brew'). This is a standard and well-known package management practice for CLI tools.
- [COMMAND_EXECUTION]: The skill facilitates the execution of the 'gemini' command-line interface to interact with Google's Gemini models for Q&A and text generation.
- [PROMPT_INJECTION]: As the skill accepts user-provided prompts to pass to the 'gemini' CLI, it possesses a surface for potential indirect prompt injection.
- Ingestion points: Positional prompt arguments passed to the 'gemini' command in SKILL.md.
- Boundary markers: None are explicitly used in the provided examples to separate instructions from user content.
- Capability inventory: Subprocess execution of the 'gemini' binary.
- Sanitization: No input sanitization or validation logic is defined within the skill documentation.
Audit Metadata