← 返回 Skills 市场
athola

Nm Phantom Computer Control

作者 athola · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
71
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install nm-phantom-computer-control
功能描述
Automate desktop GUI workflows via Claude computer use API with screenshot capture and mouse/keyboard control
安全使用建议
This skill will capture screenshots and control your mouse/keyboard via OS tools and send those interactions to Claude/Anthropic — it's powerful and can reveal private information. Before installing: 1) Confirm where the actual code lives (SKILL.md assumes code from the GitHub repo; none is bundled). 2) Expect to provide an Anthropic/Claude API key even though the registry metadata doesn't declare it; prefer skills that explicitly declare required credentials. 3) Run only in a VM/Docker sandbox or an isolated account and close all sensitive apps; test with dummy data. 4) Require human approval for any actions that have real consequences and set strict max_iterations. 5) If you need stronger assurance, ask the maintainer to (a) include explicit requires.env metadata, (b) bundle or point to a verified release artifact, and (c) provide reproducible install steps and the exact code that will run so you can audit it before use.
功能分析
Type: OpenClaw Skill Name: nm-phantom-computer-control Version: 1.0.0 The skill bundle (SKILL.md, _meta.json) describes a system for desktop GUI automation using Claude's Computer Use API, which involves high-risk capabilities such as screen capture and mouse/keyboard control via shell utilities like xdotool and scrot. While the documentation includes safety guidelines and lacks evidence of malicious intent or prompt injection, the inherent nature of the tool provides a significant attack surface for OS-level interaction. The bundle lacks the actual implementation code, instead instructing the agent to execute external CLI commands, which is a risky behavior without clear malicious proof.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The name/description and SKILL.md consistently describe a desktop GUI automation skill that uses Claude's Computer Use API and OS tools (xdotool, scrot, Xvfb). However, the registry metadata declares no required environment variables or binaries while the SKILL.md explicitly expects an ANTHROPIC_API_KEY (export example) and system binaries. That mismatch between claimed requirements and the actual instructions is an incoherence.
Instruction Scope
The SKILL.md instructs the agent to capture full-screen screenshots and perform mouse/keyboard actions (xdotool/scrot) and to supply an API key to the remote Claude/Anthropic API. Those actions are within the stated purpose but are inherently high-sensitivity (screenshots can expose private data). The file also references running Python modules (phantom.cli) and uv run, yet no code files are bundled in the skill — the instructions assume code exists externally (the GitHub repo), which is not present in the package metadata.
Install Mechanism
This is an instruction-only skill with no install spec, so nothing is written automatically to disk by the registry. SKILL.md recommends installing system packages via apt (xdotool, scrot, xclip, Xvfb) which is a normal, low-risk instruction, but installation is manual and the skill will depend on those host-level tools.
Credentials
The skill requires an API key (examples use ANTHROPIC_API_KEY / sk-ant-...) and will send screenshots to Claude/Anthropic, but the registry metadata lists no required env vars or primary credential. Requesting an API key and sending full-screen images is proportionate to the skill's function but the missing declaration is an important inconsistency and increases risk (possible unexpected exfiltration of screen contents if misused).
Persistence & Privilege
always is false and the skill does not request system-wide config paths or to modify other skills. Autonomous invocation is allowed by default (platform normal), which means the agent could run this skill without per-call approval — combine that with the screenshot/control capabilities and you should consider restricting agent autonomy when installing.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install nm-phantom-computer-control
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /nm-phantom-computer-control 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of the Computer Control skill. - Automate desktop GUI workflows using Claude computer use API. - Supports screenshot capture, mouse/keyboard control, and visual task automation. - CLI and Python interfaces provided for easy integration. - Compatibility with Opus/Sonnet/Haiku models and multiple tool versions. - Includes environment setup instructions, API version mapping, and safety guidelines.
元数据
Slug nm-phantom-computer-control
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Nm Phantom Computer Control 是什么?

Automate desktop GUI workflows via Claude computer use API with screenshot capture and mouse/keyboard control. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 71 次。

如何安装 Nm Phantom Computer Control?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install nm-phantom-computer-control」即可一键安装,无需额外配置。

Nm Phantom Computer Control 是免费的吗?

是的,Nm Phantom Computer Control 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Nm Phantom Computer Control 支持哪些平台?

Nm Phantom Computer Control 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Nm Phantom Computer Control?

由 athola(@athola)开发并维护,当前版本 v1.0.0。

💬 留言讨论