Gemini SkillBLOCK
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
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
通过 CDP 操控 Gemini 网页版,实现 AI 生图、对话、图片提取等自动化操作。
Gemini Skill
快速开始 · 报告 Bug · 提出新特性
English | 中文
「剥开了尖刺 &nb
41d2624d1c51OBSERVED · 2026-09-27Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add gemini-skill -- npx -y [email protected]
{
"mcpServers": {
"gemini-skill": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (21)
17 read · 4 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
atlas_list_models | read | |
atlas_send_message | write | |
atlas_stream_message | read | |
gemini_browser_info | read | |
gemini_check_login | read | |
gemini_download_full_size_image | read | |
gemini_extract_image | read | |
gemini_generate_image | read | |
gemini_get_all_text_responses | read | |
gemini_get_images | read | |
gemini_get_latest_text_response | read | |
gemini_navigate_to | read | |
gemini_new_chat | read | |
gemini_probe | read | |
gemini_reload_page | read | |
gemini_send_message | write | |
gemini_set_thinking_depth | write | |
gemini_share_latest_image | read | |
gemini_switch_model | read | |
gemini_temp_chat | read | |
gemini_upload_images | write |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | FAIL |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (9 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (9)
.env
const DAEMON_URL = `http://127.0.0.1:${config.daemonPort}`;browserURL: `http://127.0.0.1:${port}`,console.log(`[daemon] 🚀 Browser Daemon 已启动 — http://127.0.0.1:${PORT}`);const daemonUrl = `http://127.0.0.1:${config.daemonPort}`;.env
@modelcontextprotocol/sdk, puppeteer-core, puppeteer-extra, puppeteer-extra-plugin-stealth, sharp
markdown/example.png
markdown/example2.png
Gates applied: no_behavioural_pass.
41d2624d1c51full audit observations/trust-audit/mcp-server/wjz-p__gemini-skill.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-27 | 41d2624d1c51 | BLOCK | D | 69 | first audit |
Questions
What is the Gemini Skill MCP server?
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
What tools does Gemini Skill expose?
21 in total: 17 read-only, 4 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Gemini Skill safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What credentials does Gemini Skill need?
No credential environment variables were found in its source, so it appears to need none.
How does Gemini Skill run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as gemini-skill at 1.1.1.
How current is this page?
The grade is for one exact copy of the source (41d2624d1c51), read on 2026-09-27. The repository is watched and re-audited when it changes.