AgentArmorHQ
Sign in

gemini-skill

Skill · GitHub · ★ 832 · graded 2026-10-25Source linked

gemini drawing MCP & skill through browser, can be used in openclaw or any agent that supports MCP. Gemini画图 MCP和sill，支持龙虾或任何agent使用٩(๑>◡<๑)۶

No outside reports on file

This tool gives an AI direct access to your Gemini account and image generation quota, so keep API keys secure and watch for unexpected image generation activity.

Based on public adoption and transparency signals as of Oct 25, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Gemini Skill helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachFetches arbitrary web URLsREVIEW
  • CredentialsRequires API key or tokenREVIEW
  • Package sourceGitHub (WJZ-P/gemini-skill)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/WJZ-P/gemini-skill ↗

All setup options ↓

Check this skillWatch it in my stackCompareAdd to allowlistREADME badgeView project

About Gemini Skill

This is a skill that lets AI agents (like those using OpenClaw) draw images through Google's Gemini API. It connects as a plugin called MCP (Model Context Protocol) so agents can request and generate drawings.

Who it’s for

Developers building AI agents who want to add image generation features. It works with agent systems that support the MCP plugin standard.

Alternatives

  • DALL-E 3 skill: OpenAI's image generation integrated into agents (better commercial support)
  • Stable Diffusion local: Run image generation on your own hardware (no external API needed)
  • Claude vision + image generation: Anthropic's built-in image capabilities for agents
  • MidJourney API wrapper: Alternative agent skill for MidJourney image requests

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README on GitHub for installation steps, as setup may vary based on your agent framework (OpenClaw or other MCP-compatible systems).

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

32/100
GitHub stars
832
Listing last refreshed
2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Security reports

No reports found for this package in our research (last checked 2026-10-30).

Check a specific version →

Risks to watch for

  • API key exposure: Stores your Gemini API credentials, which could let attackers generate images at your expense or steal the key from config files
  • Unlimited image generation: Without rate limits, an attacker controlling the agent could generate thousands of images to drain your account or API quota
  • Malicious prompts: If the AI can be tricked into specific drawing requests, it might create unwanted or harmful content tied to your account
  • Data in images: Agents might accidentally include sensitive info (like file paths or internal data) in image generation requests sent to Google
  • Web browser risks: If it runs drawing commands through a browser, malicious web pages could hijack the process or inject commands

How to lower the risk

Least-privilege permissions

  • Use a dedicated Gemini API key only for this agent, not your main account key
  • Limit the agent's ability to accept drawing requests to trusted sources only

Network isolation

  • Run the agent in a sandbox or isolated environment when testing unknown code
  • Use firewall rules to block unusual outbound API calls to Google services

Monitoring

  • Check your Gemini API usage dashboard regularly for spikes in image generation
  • Log all drawing requests the agent makes and review them weekly

Red flags to watch for

  • Unexpected charges or quota usage on your Gemini account
  • The agent trying to generate images with bizarre or sensitive prompts
  • Config files or logs containing your actual API key in plain text

Questions

How do I install Gemini Skill?

Gemini Skill does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/WJZ-P/gemini-skill.

Are there security reports about Gemini Skill?

No reports found for this package in our research (last checked 2026-10-30). Gemini Skill currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include api key exposure, unlimited image generation, malicious prompts.

Is Gemini Skill actively maintained?

Gemini Skill has 832 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/WJZ-P/gemini-skill before pinning it in production.

What are alternatives to Gemini Skill?

Notable alternatives to Gemini Skill include DALL-E 3 skill (OpenAI's image generation integrated into agents (better commercial support)), Stable Diffusion local (Run image generation on your own hardware (no external API needed)), Claude vision + image generation (Anthropic's built-in image capabilities for agents), MidJourney API wrapper (Alternative agent skill for MidJourney image requests). You can also compare Gemini Skill side by side with other skills in the Related tools section on this page.

README badge and team notes

Maintain or use Gemini Skill? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for Gemini Skill

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for Gemini Skill](https://agentarmorhq.com/api/badge/wjz-p-gemini-skill)](https://agentarmorhq.com/skills/wjz-p-gemini-skill)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/wjz-p-gemini-skill"><img src="https://agentarmorhq.com/api/badge/wjz-p-gemini-skill" alt="AgentArmorHQ Risk Grade for Gemini Skill" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "wjz-p-gemini-skill"

Share with your security lead

Need sign-off to use gemini-skill? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: gemini-skill
- **Listing URL:** https://agentarmorhq.com/skills/wjz-p-gemini-skill
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 832 GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Fetches arbitrary web URLs
- **Credentials:** Requires API key or token
- **Package source:** GitHub (WJZ-P/gemini-skill)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/WJZ-P/gemini-skill
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 25, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
AI agent skill
Publisher
WJZ-P
Source code
github.com/WJZ-P/gemini-skill
Est. context load
~62 tokens idle · ~450 tokens when active (on-demand skill)
Popularity
832 GitHub stars
Last updated
2026-10-29
Last graded
2026-10-25

Community

Discussions for Gemini Skill

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Gemini Skill helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude