← 返回 Skills 市场
388
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install volc-vision
功能描述
使用火山引擎 ARK API 做图片理解、图片描述、视觉问答与图像分析。适用于用户发来图片并询问“这是什么”“图里有什么”“帮我看下这张图”“描述一下图片内容”“识别图片中的信息”等场景，也适用于需要对本地图片、图片 URL 或 base64 图片做理解和问答时。
安全使用建议
This skill is coherent with its stated purpose, but be aware it will send any image you pass (including local files) to an external ARK service using the ARK_API_KEY. Only provide non-sensitive images and only supply an API key you trust to be used with that external service. Verify the API hostname and your operator's policy for sending images to third-party APIs before installing. If you need to restrict uploads, avoid passing arbitrary filesystem paths or base64 of sensitive content to the skill.
功能分析
Type: OpenClaw Skill
Name: volc-vision
Version: 0.1.0
The volc-vision skill is a legitimate integration for image analysis using the Volcengine ARK API. The code in index.js reads local or remote images and sends them along with the user's API key to the official Volcengine endpoint (ark.cn-beijing.volces.com). No evidence of malicious intent, data exfiltration to unauthorized domains, or prompt injection attacks was found.
能力评估
Purpose & Capability
Name/description, required binary (node), and required env var (ARK_API_KEY) align with a tool that calls an external vision API. The code uses the ARK API key to authenticate requests to an ARK endpoint, which is expected for this purpose.
Instruction Scope
SKILL.md and index.js instruct reading images from local paths, URLs, or data URLs and sending them (as base64 data URLs) to the external ARK API. That is necessary for the stated purpose, but it means any local file path passed to the skill will be read and transmitted externally — a privacy/exfiltration risk if sensitive files are supplied.
Install Mechanism
No install spec; this is instruction + a single Node script. The only runtime requirement is node on PATH. Nothing is downloaded or written to disk by an installer step.
Credentials
Only ARK_API_KEY (primary credential) is required, which is proportionate to calling an authenticated external API. The code uses that key in an Authorization header as expected. No unrelated secrets or config paths are requested.
Persistence & Privilege
Skill is not always-enabled and does not request elevated platform privileges or modify other skills. It does not persist credentials itself. Autonomous invocation is allowed (platform default) but not combined with other concerning privileges.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install volc-vision - 安装完成后，直接呼叫该 Skill 的名称或使用
/volc-vision触发 - 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
v0.1.0
首次发布：补充标准 frontmatter、中文触发描述、依赖说明与环境变量要求。
元数据
常见问题
volc-vision 是什么？
使用火山引擎 ARK API 做图片理解、图片描述、视觉问答与图像分析。适用于用户发来图片并询问“这是什么”“图里有什么”“帮我看下这张图”“描述一下图片内容”“识别图片中的信息”等场景，也适用于需要对本地图片、图片 URL 或 base64 图片做理解和问答时。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 388 次。
如何安装 volc-vision？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install volc-vision」即可一键安装，无需额外配置。
volc-vision 是免费的吗？
是的，volc-vision 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
volc-vision 支持哪些平台？
volc-vision 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 volc-vision？
由 big-dust（@big-dust）开发并维护，当前版本 v0.1.0。
推荐 Skills