gemini

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gemini command-line utility to perform one-shot Q&A and manage extensions. This is the intended functionality of the tool.
  • [EXTERNAL_DOWNLOADS]: The skill's metadata provides instructions to install the gemini-cli package via Homebrew, which is a standard and verifiable installation method.
  • [PROMPT_INJECTION]: While the skill involves processing user prompts, it proactively includes safety guidance to avoid the --yolo flag, which reduces the risk of unintended command execution resulting from model output.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 09:13 PM
Security Audit — agent-trust-hub — gemini