← 返回 Skills 市场
guyoung

Boxed FFmpeg

作者 guyoung · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
94
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install boxed-ffmpeg
功能描述
Audio/video information extraction, format conversion, and audio extraction using FFmpeg WASM sandbox.
使用说明 (SKILL.md)

Boxed FFmpeg Skill

Run FFmpeg commands safely within a WASM sandbox for audio/video processing.

Triggering

Use this skill when the user says:

  • "ffmpeg", "media info", "get video information"
  • "convert video", "change video format", "格式转换"
  • "extract audio", "audio from video", "提取音频"
  • "boxed-ffmpeg"

⚠️ Required Plugin

This skill requires the openclaw-wasm-sandbox plugin version >= 0.2.0.

openclaw plugins install clawhub:openclaw-wasm-sandbox
openclaw plugins update openclaw-wasm-sandbox
openclaw gateway restart

⚠️ WASM File Required

If the WASM file does not exist, download it first:

wasm-sandbox-download({
  url: "https://raw.githubusercontent.com/guyoung/wasm-sandbox-openclaw-skills/main/boxed-ffmpeg/files/boxed-ffmpeg-component.wasm",
  output: "~/.openclaw/skills/boxed-ffmpeg/files/boxed-ffmpeg-component.wasm",
  resume: false,
  timeout: 120000
})

Tool: wasm-sandbox-run

wasm-sandbox-run({
  wasmFile: "~/.openclaw/skills/boxed-ffmpeg/files/boxed-ffmpeg-component.wasm",
  workDir: "\x3Cinput-file-directory>",
  args: ["\x3CCOMMAND>", "\x3CINPUT>", "\x3COUTPUT>"]
})

Important:

  • workDir must be set to the directory containing the input file
  • Input/output arguments are filenames only (no directory paths)

Commands

Command Description Arguments
info Get media file information \x3CINPUT>
convert Convert video format \x3CINPUT> \x3COUTPUT>
extract-audio Extract audio from video \x3CINPUT> \x3COUTPUT>

Examples

Get Media Information

User says: "Get info about video.mp4" (file in workspace root)

wasm-sandbox-run({
  wasmFile: "~/.openclaw/skills/boxed-ffmpeg/files/boxed-ffmpeg-component.wasm",
  workDir: "/home/user/.openclaw/workspace",
  args: ["info", "video.mp4"]
})

Convert Video Format

User says: "Convert video.mp4 to AVI" (file in workspace root)

wasm-sandbox-run({
  wasmFile: "~/.openclaw/skills/boxed-ffmpeg/files/boxed-ffmpeg-component.wasm",
  workDir: "/home/user/.openclaw/workspace",
  args: ["convert", "video.mp4", "video.avi"]
})

Extract Audio from Video

User says: "Extract audio from video.mp4 as mp3" (file in workspace root)

wasm-sandbox-run({
  wasmFile: "~/.openclaw/skills/boxed-ffmpeg/files/boxed-ffmpeg-component.wasm",
  workDir: "/home/user/.openclaw/workspace",
  args: ["extract-audio", "video.mp4", "audio.mp3"]
})

Convert with Subdirectory

User says: "Convert videos/input.mp4 to videos/output.avi"

wasm-sandbox-run({
  wasmFile: "~/.openclaw/skills/boxed-ffmpeg/files/boxed-ffmpeg-component.wasm",
  workDir: "/home/user/.openclaw/workspace/videos",
  args: ["convert", "input.mp4", "output.avi"]
})

Important Notes

  • workDir is required — must be the directory of the input file
  • Input/output are filenames only — no paths, just names
  • Output file appears in workDir after successful execution
  • No network access needed — all processing is local
安全使用建议
This skill appears to do what it says (FFmpeg in a WASM sandbox) but requires installing a plugin and downloading a WASM binary from a third-party GitHub repo without any checksum or signature. Before installing: (1) Verify the openclaw-wasm-sandbox plugin source and inspect its code/reviews; (2) verify the boxed-ffmpeg-component.wasm provenance — prefer a signed/pinned release or a trusted org repo; (3) if possible, download the WASM manually, verify its integrity, and place it locally rather than letting the agent fetch it automatically; (4) do not set workDir to sensitive system directories — use an isolated workspace; (5) consider testing the plugin and WASM inside an isolated VM/container first; (6) require explicit user consent for plugin installation and gateway restart. If you cannot verify the plugin and WASM authorship and integrity, treat this skill as higher-risk and avoid installing it on sensitive systems.
功能分析
Type: OpenClaw Skill Name: boxed-ffmpeg Version: 1.0.0 The skill provides media processing capabilities by instructing the agent to download a remote WASM binary from a personal GitHub repository (guyoung/wasm-sandbox-openclaw-skills) and execute it using a sandbox tool. While this behavior is consistent with the stated goal of providing a 'boxed' FFmpeg environment, the automated downloading and execution of remote payloads (SKILL.md) is a high-risk capability. No clear evidence of malicious intent, such as data exfiltration or unauthorized access, was found, but the reliance on an unverified external binary warrants a suspicious classification.
能力评估
✓ Purpose & Capability
The name/description (Boxed FFmpeg) match the runtime instructions: it requires a WASM sandbox plugin and a boxed-ffmpeg.wasm component and shows how to run ffmpeg-like commands via wasm-sandbox-run. There are no unrelated environment variables or extraneous capabilities requested.
ℹ Instruction Scope
Instructions stay within the stated purpose (run FFmpeg-like operations in a WASM sandbox). They only reference workspace directories and the skill-specific path under ~/.openclaw/skills. However, the runtime steps instruct downloading and executing a WASM binary; while the skill claims 'no network access needed' for processing, it still requires an initial network download of the WASM file, and the agent is asked to write that binary into the skills directory.
⚠ Install Mechanism
There is no formal install spec, but SKILL.md requires installing the openclaw-wasm-sandbox plugin and explicitly provides a raw GitHub URL to download a WASM component from a user repo (guyoung/... on raw.githubusercontent.com). Downloading and executing an unsigned WASM from an arbitrary user repository and placing it under ~/.openclaw/skills is high-risk because there is no checksum/signature, no pinned release, and the source repo is not described or verified. The plugin installation and gateway restart steps also alter the agent environment and should be reviewed before proceeding.
✓ Credentials
The skill requests no environment variables, credentials, or config paths. That is proportionate. One important note: the skill requires setting workDir to the directory containing input files — any files inside that directory will be accessible to the WASM component, so avoid using sensitive system directories.
⚠ Persistence & Privilege
The skill does not request 'always: true', but it requires installing a plugin and restarting the OpenClaw gateway, which modifies the agent runtime environment. Combined with the remote WASM download and autonomous invocation being allowed (default), this increases the blast radius: a downloaded WASM run by the sandbox could be invoked by the agent repeatedly without further confirmation. That combination is worth caution even though autonomous invocation itself is normal.
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 boxed-ffmpeg
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /boxed-ffmpeg 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 boxed-ffmpeg. - Run FFmpeg commands securely in a WASM sandbox for audio/video file processing. - Supports media information extraction, video format conversion, and audio extraction. - Requires the openclaw-wasm-sandbox plugin (≥ 0.2.0) and the boxed-ffmpeg WASM file. - Skill usage is triggered by common audio/video conversion and extraction phrases. - Clear usage instructions and example commands provided for workspace and subdirectory scenarios.
元数据
Slug boxed-ffmpeg
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Boxed FFmpeg 是什么？

Audio/video information extraction, format conversion, and audio extraction using FFmpeg WASM sandbox. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 94 次。

如何安装 Boxed FFmpeg？

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

Boxed FFmpeg 是免费的吗？

是的，Boxed FFmpeg 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Boxed FFmpeg 支持哪些平台？

Boxed FFmpeg 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 Boxed FFmpeg？

由 guyoung（@guyoung）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191113 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论