← Back to Skills Marketplace
godzff

飞书媒体发送

by godzff · GitHub ↗ · v1.1.0
cross-platform ⚠ suspicious
665
Downloads
0
Stars
8
Active Installs
2
Versions
Install in OpenClaw
/install feishu-media
Description
飞书媒体文件发送技能。适用于:发送文件、图片、URL图片、视频、音频、语音消息,以及打包压缩后发送。当用户要求在飞书中发送任何类型的媒体文件时激活此技能。
README (SKILL.md)

飞书媒体发送技能

通过 message 工具向飞书发送各类媒体文件。

核心用法

所有媒体发送都通过 message 工具的 action=send,关键参数:

  • channel: feishu
  • target: chat:群IDuser:open_id(省略则回复当前会话)
  • message: 附带的文字说明(可选)
  • filePath: 本地文件路径
  • media: URL 地址(网络图片/文件)

1. 发送本地文件(PDF/DOC/XLS/PPT/TXT等)

message action=send channel=feishu filePath=/path/to/file.pdf message="文件说明"

支持格式:pdf, doc/docx, xls/xlsx, ppt/pptx, txt, csv, zip, tar.gz 等。

2. 发送本地图片

message action=send channel=feishu filePath=/path/to/image.png message="图片说明"

支持格式:jpg, jpeg, png, gif, webp, bmp。

3. 发送 URL 图片

message action=send channel=feishu media=https://example.com/image.png message="网络图片"

4. 发送视频

message action=send channel=feishu filePath=/path/to/video.mp4 message="视频说明"

视频以文件附件形式发送(飞书 msg_type: file)。支持 mp4, mov, avi。

5. 发送音频(非语音)

MP3 等音频文件作为普通文件发送:

message action=send channel=feishu filePath=/path/to/audio.mp3 message="音频文件"

6. 发送语音消息(可播放的语音条)

语音消息需要 Ogg/Opus 格式。飞书会显示为可播放的语音条。

6.1 直接发送 opus/ogg 文件

message action=send channel=feishu filePath=/path/to/voice.opus message="语音消息"

6.2 从 MP3 转换后发送

先用 ffmpeg 转换格式:

ffmpeg -i input.mp3 -ar 16000 -ac 1 -acodec libopus output.ogg -y

然后发送 output.ogg。

6.3 技术细节

语音消息的底层流程:

  1. 上传:im.file.createfile_type: "opus",需带 duration(毫秒)
  2. 发送:msg_type: "audio",content: {"file_key":"xxx","duration":3007}
  3. duration 由 ffprobe 自动获取,无需手动指定

7. 打压缩包后发送

当需要发送多个文件或不支持的格式时,先打包再发送:

7.1 打 zip 包

zip -j /tmp/archive.zip /path/to/file1 /path/to/file2

7.2 打 tar.gz 包

tar czf /tmp/archive.tar.gz -C /path/to/dir .

7.3 发送压缩包

message action=send channel=feishu filePath=/tmp/archive.zip message="打包文件"

格式支持速查表

类型 格式 发送方式 飞书显示
图片 jpg/png/gif/webp filePath 或 media(URL) 内嵌图片
文档 pdf/doc/xls/ppt filePath 文件卡片
视频 mp4/mov/avi filePath 文件卡片
音频 mp3/wav/flac filePath 文件卡片
语音 opus/ogg filePath 可播放语音条
压缩包 zip/tar.gz filePath 文件卡片
网络图片 URL media 内嵌图片

注意事项

  • 文件大小限制:默认 30MB
  • 语音必须是 Ogg/Opus 格式才能显示为语音条,其他音频格式只能作为文件发送
  • 需要 ffmpeg/ffprobe 支持语音格式转换和时长检测
  • 飞书应用需要 im:messageim:resource 权限
Usage Guidance
This skill appears to do what it says (send media to Feishu) but verify three things before installing: (1) Confirm your agent/platform already provides Feishu authorization (app token/credentials) and that the required Feishu app permissions (im:message, im:resource) are scoped appropriately. (2) Install ffmpeg/ffprobe from a trusted source if you need voice conversion/duration detection — SKILL.md expects them but they are not declared in metadata. (3) Be cautious about which files you instruct the skill to send: it accepts arbitrary local file paths and URLs, so don’t ask it to send sensitive files (passwords, private keys, credential stores) unless you intentionally want them transmitted. If you need stronger safety, request the skill declare explicit binary and credential requirements or add guardrails limiting allowed file paths/types.
Capability Analysis
Type: OpenClaw Skill Name: feishu-media Version: 1.1.0 The skill is suspicious due to multiple potential vulnerabilities arising from its instructions to the AI agent. The `SKILL.md` explicitly instructs the agent to execute shell commands (`ffmpeg`, `zip`, `tar`) without specifying input sanitization, creating a high risk of shell injection if user-provided input is used in command arguments. Furthermore, the `filePath` parameter for sending messages allows specifying arbitrary local file paths, which could be abused for local file disclosure or exfiltration (e.g., sending sensitive system files). The `media` parameter also allows fetching content from arbitrary URLs, posing a potential SSRF risk. These are critical vulnerabilities, but there is no clear evidence of intentional malicious behavior by the skill developer.
Capability Assessment
Purpose & Capability
Name/description and runtime instructions are aligned: the skill sends local files, URLs, videos, audio, and compressed archives to Feishu. However SKILL.md references ffmpeg/ffprobe for audio conversion/duration yet the skill metadata declares no required binaries. Also the README notes Feishu app permissions (im:message, im:resource) but the skill declares no credentials or environment variables — it assumes the host/agent already has Feishu authorization configured.
Instruction Scope
Instructions focus on sending media via a 'message' tool with channel=feishu and accept arbitrary filePath or media URL inputs — this is expected, but it means the skill can read and transmit any local files the agent is instructed to send. There are no guardrails or limits described beyond a generic 30MB limit. The instructions also call out ffmpeg/ffprobe usage but don't declare them as required binaries.
Install Mechanism
Instruction-only skill with no install steps and no code files; nothing is written to disk by an installer. This is the lowest-risk install mechanism.
Credentials
The skill declares no required environment variables or primary credential, which is plausible if the platform supplies Feishu credentials via the 'message' tool. Still, the SKILL.md explicitly requires Feishu app permissions and external binaries (ffmpeg/ffprobe). The lack of explicit credential requirements means you should confirm where and how Feishu auth is provided by your agent/platform before trusting it.
Persistence & Privilege
always is false, user-invocable is true, and model invocation is allowed — standard settings for a skill of this type. The skill does not request persistent or cross-skill configuration changes.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install feishu-media
  3. After installation, invoke the skill by name or use /feishu-media
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
完善语音消息支持:opus上传+audio发送+ffprobe自动获取duration
v1.0.0
初始版本:支持文件/图片/URL图片/视频/音频/语音/压缩包发送
Metadata
Slug feishu-media
Version 1.1.0
License
All-time Installs 9
Active Installs 8
Total Versions 2
Frequently Asked Questions

What is 飞书媒体发送?

飞书媒体文件发送技能。适用于:发送文件、图片、URL图片、视频、音频、语音消息,以及打包压缩后发送。当用户要求在飞书中发送任何类型的媒体文件时激活此技能。 It is an AI Agent Skill for Claude Code / OpenClaw, with 665 downloads so far.

How do I install 飞书媒体发送?

Run "/install feishu-media" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 飞书媒体发送 free?

Yes, 飞书媒体发送 is completely free (open-source). You can download, install and use it at no cost.

Which platforms does 飞书媒体发送 support?

飞书媒体发送 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 飞书媒体发送?

It is built and maintained by godzff (@godzff); the current version is v1.1.0.

💬 Comments