gemini
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS] (SAFE): The skill specifies installation of the
gemini-clipackage via Homebrew (brew). The provided homepage (ai.google.dev) belongs to a trusted organization (Google), and the package is a standard utility for the service. - [COMMAND_EXECUTION] (SAFE): The skill defines commands to run the
geminibinary with user-provided prompts. These are standard operations for a CLI-based agent skill and do not include malicious subprocess spawning or shell escapes. - [PROMPT_INJECTION] (SAFE): No instructions attempting to bypass safety filters, extract system prompts, or override agent behavior were detected in the skill content.
- [DATA_EXFILTRATION] (SAFE): There are no hardcoded credentials, sensitive file path accesses, or suspicious network exfiltration patterns. The authentication flow described uses the official interactive login method.
Audit Metadata