← 返回 Skills 市场
jonisjongithub

Venice Ai

作者 jonisjongithub · GitHub ↗ · v2.1.1 · MIT-0
cross-platform ✓ 安全检测通过
2811
总下载
3
收藏
7
当前安装
5
版本数
在 OpenClaw 中安装
/install venice-ai
功能描述
Complete Venice AI platform — text generation, vision/image analysis, web search, X/Twitter search, embeddings, TTS, speech-to-text, image generation, backgr...
安全使用建议
This skill is a coherent Venice AI CLI client and requires only python3 and a Venice API key. Main things to consider before installing: 1) The scripts will fetch any HTTP(S) URL you pass (images/videos/audio). Do not supply internal or metadata URLs (localhost, 169.254.x.x, internal hostnames) in multi-tenant or exposed environments — this is an SSRF risk. 2) The skill will look for your VENICE_API_KEY in the environment and, as a documented fallback, in ~/.clawdbot/clawdbot.json; if you store the key there, treat that file as sensitive. 3) The code is pure Python and open-source (no obfuscated binaries), but some small coding bugs/quirks exist (e.g., unusual GET-with-body usage); these look like bugs, not malicious behavior. 4) If you run this on a shared host, sandbox or restrict outbound network access to prevent accidental requests to internal resources. If you need higher assurance, review venice_common.py to confirm API_BASE points to api.venice.ai and verify key-handling behavior before use.
功能分析
Type: OpenClaw Skill Name: venice-ai Version: 2.1.1 The venice-ai skill bundle is a comprehensive and well-documented integration for the Venice AI platform, covering text, vision, image, video, and audio capabilities. The scripts (e.g., venice.py, venice-image.py) are transparent wrappers around the official Venice API (api.venice.ai) using Python's standard library. Security considerations, such as the risk of SSRF when fetching user-provided URLs, are explicitly addressed in SECURITY.md. The skill follows standard OpenClaw patterns for API key management and media output without any evidence of malicious intent, obfuscation, or prompt injection attacks.
能力标签
crypto
能力评估
Purpose & Capability
Name/description (complete Venice AI client) matches the code and declared requirements: Python scripts that call Venice endpoints and a single required credential VENICE_API_KEY. The brew install for python is reasonable. Minor note: the SKILL.md and SECURITY.md reference reading the Clawdbot config (~/.clawdbot/clawdbot.json) as a fallback for the API key, but the registry metadata did not list that config path as a required config path — this is a small metadata omission rather than a functional mismatch.
Instruction Scope
Runtime instructions and scripts accept and fetch user-supplied URLs (images, videos, etc.) and upload content to api.venice.ai. That behavior is legitimate for an image/video/audio processing client, but it creates SSRF risk if untrusted/internal URLs are supplied. The project documents this risk in SECURITY.md but does not enforce any outbound URL restrictions in code. Also some small coding oddities exist (e.g., GET request constructed with a JSON body in one function) that look like bugs rather than malicious behavior.
Install Mechanism
Install spec only recommends installing Python via Homebrew (formula: python). No downloads from arbitrary URLs or extract/install steps are present. The skill ships as Python source scripts (no opaque binary installs).
Credentials
Only a single credential (VENICE_API_KEY) is required and used as the Authorization bearer token to contact api.venice.ai. That is proportional to the functionality. The fallback to read ~/.clawdbot/clawdbot.json for the key is documented but not declared in registry config paths — users should be aware the skill may read that file if present.
Persistence & Privilege
The skill does not request always:true or other elevated platform privileges and appears not to modify other skills or global config. It runs as CLI scripts invoked by the agent and only writes files the user requests via --output or --out-dir.
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 venice-ai
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /venice-ai 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
v2.1.1
Fixed SECURITY.md to accurately document URL fetching behavior. The skill fetches user-supplied URLs for image/video inputs, which was previously understated. Added SSRF considerations section.
v2.1.0
Added: Vision/image analysis (analyze command), background removal, multi-edit (up to 3 images), music generation (venice-music.py), X/Twitter search (--x-search for Grok models), E2EE support (--enable-e2ee), expanded reasoning effort values (none/minimal/low/medium/high/xhigh/max). Updated SKILL.md with TEE/E2EE privacy tiers documentation.
v2.0.0
🎉 Major update: Merged venice-ai-media into unified skill **New in v2.0.0:** - Complete Venice platform in one skill (text, audio, images, video) - Added image generation (Flux, GPT-Image, etc.) - Added video creation (Sora, WAN, Runway) - Added image upscaling with AI enhancement - Added AI image editing - Backward compatible with existing venice-ai-media configs One skill to unlock everything Venice has to offer!
v1.0.1
Updated skill
v1.0.0
Venice AI 1.0.0 — Initial Release - Introduces the full Venice AI platform skill with private, uncensored AI inference. - Supports model discovery, text generation with web search/citations, embeddings, TTS, speech-to-text, and model comparison. - Compatible with 30+ models, including GPT-5.2 and Claude Opus 4.5; supports advanced features like character personas and reasoning control. - OpenAI-compatible API; easy setup using environment variables or Clawdbot config. - Includes a comprehensive CLI for all workflows with detailed usage instructions.
元数据
Slug venice-ai
版本 2.1.1
许可证 MIT-0
累计安装 9
当前安装数 7
历史版本数 5
常见问题

Venice Ai 是什么?

Complete Venice AI platform — text generation, vision/image analysis, web search, X/Twitter search, embeddings, TTS, speech-to-text, image generation, backgr... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 2811 次。

如何安装 Venice Ai?

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

Venice Ai 是免费的吗?

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

Venice Ai 支持哪些平台?

Venice Ai 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 Venice Ai?

由 jonisjongithub(@jonisjongithub)开发并维护,当前版本 v2.1.1。

💬 留言讨论