name: gemini description: Gemini CLI for one-shot Q&A, summaries, and generation. homepage: https://ai.google.dev/ metadata: {"clawdbot":{"emoji":"♊️","requires":{"bins":["gemini"]},"install":[{"id":"brew","kind":"brew","formula":"gemini-cli","bins":["gemini"],"label":"Install Gemini CLI (brew)"}]}}

Gemini CLI

Use Gemini in one-shot mode with a positional prompt (avoid interactive mode).

Quick start

gemini "Answer this question..."
gemini --model <name> "Prompt..."
gemini --output-format json "Return JSON"

Extensions

List: gemini --list-extensions
Manage: gemini extensions <command>

Notes

If auth is required, run gemini once interactively and follow the login flow.
Avoid --yolo for safety.

Security Scan

Status

suspicious

Open VirusTotal

OpenClaw

gpt-5-mini

suspicious

OpenClaw analysis

The skill is generally consistent with a thin wrapper around the Gemini CLI, but there are metadata inconsistencies (SKILL.md advertises a required 'gemini' binary and a brew install while the registry metadata lists no requirements/install), so verify the CLI source before installing.

Confidence: medium

VirusTotal

Type: OpenClaw Skill Name: gemini Version: 1.0.0 The skill bundle is benign. It defines an OpenClaw skill to interact with the Gemini CLI, providing installation instructions via `brew` and usage examples. All instructions in `SKILL.md` are directly related to the stated purpose of using the `gemini` command-line tool. There is no evidence of data exfiltration, malicious execution, persistence, or prompt injection attempts against the agent. Notably, the `SKILL.md` even includes a safety instruction to 'Avoid `--yolo` for safety'.

Gemini