SiliconFlow Video Gen

Generate videos using SiliconFlow API with Wan2.2 model. Supports both Text-to-Video and Image-to-Video.

Security Scan

The skill is internally consistent with a video-generation integration: it requires one provider API key, reads an OpenClaw config for that key, and sends generation requests to api.siliconflow.cn; minor metadata mismatches were found but nothing indicates malicious behavior.

Purpose & Capability

The skill's code, SKILL.md, README, and skill.json all describe a SiliconFlow video-generation integration and require a SILICONFLOW_API_KEY — this is appropriate for the stated purpose. Minor inconsistencies exist in the registry header: the top-level summary said "Required env vars: none" and "Homepage: none", while skill.json and SKILL.md declare SILICONFLOW_API_KEY as required and skill.json includes a homepage. These metadata mismatches are likely bookkeeping issues rather than malicious intent, but they should be corrected.

Instruction Scope

SKILL.md and the script limit actions to reading the SILICONFLOW_API_KEY (env or ~/.openclaw/openclaw.json), building a JSON request with the user prompt (and optional image URL), and POSTing to https://api.siliconflow.cn/v1/video/submit. The script does not attempt to read other files, credentials, or transmit data to third-party endpoints. Using curl via subprocess is expected here and aligns with the described functionality.

Install Mechanism

There is no automated install spec included (instruction-only install via 'npx clawhub install' or manual clone). No downloads from third-party URLs or archive extraction are present in the package. The presence of a single Python script and docs means nothing arbitrary will be written or executed at install time beyond the user's explicit install action.

Credentials

The only secret the skill requires is SILICONFLOW_API_KEY, which is proportionate for calling the SiliconFlow API. One note: the top-level registry metadata reported 'Required env vars: none' despite skill.json and SKILL.md declaring SILICONFLOW_API_KEY as required — this mismatch should be resolved. There are no other credentials or unrelated environment variables requested.

Persistence & Privilege

The skill does not request permanent presence (always:false) and does not modify other skills or system-wide settings. It uses subprocess execution (curl) to call the API, which is expected for this use case. There is no indication of elevated privileges or persistent background behavior.

Assessment

This skill appears to do what it says: it needs a SiliconFlow API key and will send prompts (and optional image URLs) to api.siliconflow.cn to request video generation. Before installing or providing an API key: 1) Verify the SiliconFlow API domain (api.siliconflow.cn) is the legitimate service you expect. 2) Prefer to create a restricted API key (scoped or rate-limited) rather than using a high-privilege key. 3) Review scripts/generate.py yourself (it’s short and readable) to confirm there are no additional network destinations. 4) Correct the metadata mismatch (registry-level 'required env' vs skill.json) or ask the publisher to fix it — mismatched metadata is usually a bookkeeping error but should be clarified. 5) If you need stricter isolation, run the script in a sandbox or environment with only the minimal network and file access necessary.

SiliconFlow Video Generation Skill

Generate videos using SiliconFlow API with Wan2.2 model. Supports both Text-to-Video and Image-to-Video.

Features

• 🎬 Text-to-Video: Generate videos from text descriptions
• 🖼️ Image-to-Video: Animate static images with motion
• 🎥 Cinematic Quality: Powered by Wan2.2 (14B params)
• 🔑 Auto API Key Detection: Reads from environment or OpenClaw config

Requirements

• Environment Variable: SILICONFLOW_API_KEY
• Optional Config File: ~/.openclaw/openclaw.json (for auto-detect)

Installation

npx clawhub install siliconflow-video-gen

Configuration

Set your SiliconFlow API key:

export SILICONFLOW_API_KEY="your-api-key"

Or configure in OpenClaw:

{
  "models": {
    "providers": {
      "siliconflow": {
        "apiKey": "your-api-key"
      }
    }
  }
}

Usage

Text-to-Video

python3 scripts/generate.py "A woman walking in a blooming garden, cinematic shot"

Image-to-Video

python3 scripts/generate.py "Camera slowly zooming in" --image-url https://example.com/image.jpg

Models

Model	Type	Cost
Wan-AI/Wan2.2-T2V-A14B	Text-to-Video	¥2/video
Wan-AI/Wan2.2-T2V-A14B	Image-to-Video	¥2/video

Security Notes

• This skill requires an API key to call SiliconFlow services
• The script reads ~/.openclaw/openclaw.json only to auto-detect API keys
• No sensitive data is transmitted except to api.siliconflow.cn
• Review the code at scripts/generate.py before providing credentials

Author

MaxStorm Team

License

MIT