← Back to Skills Marketplace
darker314159

runninghub-video

by balckbeeai · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
52
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install runninghub-video
Description
Use RunningHub official standard-model APIs for image-to-video generation. Trigger when the user asks to use RunningHub, 可灵, Seedance, 万相, or other RunningHu...
Usage Guidance
This skill will upload any local images you give it to https://www.runninghub.cn and will attempt to use an API key. Before installing or running it: (1) Be aware you must provide a RunningHub API key (via --api-key or the RUNNINGHUB_API_KEY environment variable); the skill metadata incorrectly omits this. (2) Inspect the script yourself — it reads local files and (on Windows) will try to read HKCU\Environment for RUNNINGHUB_API_KEY. (3) If you do not want your API key or files transmitted, do not run the script; consider running it in an isolated environment or supplying the key on the CLI for more control. (4) If you plan to install the skill for others, request the author fix the metadata to declare the required env var and document the registry access. (5) If you need more assurance, ask the publisher for an authoritative homepage or source repository to verify origin and review the remainder of the code (the provided script was truncated in the manifest listing — verify the complete file before use).
Capability Analysis
Type: OpenClaw Skill Name: runninghub-video Version: 1.0.0 The skill is a legitimate tool for interacting with the RunningHub image-to-video API. It includes a Python script (runninghub_video.py) that manages file uploads, task polling, and result downloads from runninghub.cn. The script's use of the Windows Registry (winreg) to retrieve the API key is a standard method for accessing persistent environment variables on that platform. No malicious behaviors such as data exfiltration, unauthorized execution, or prompt injection were found; the code logic is transparent and aligned with the stated purpose.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
The skill's name, SKILL.md, API reference, and script all align with the stated purpose (submit image-to-video jobs, poll /openapi/v2/query, upload local files, download outputs). However the declared registry metadata lists no required environment variables or primary credential while the included script clearly requires an API key (RUNNINGHUB_API_KEY or --api-key). This metadata omission is an inconsistency.
Instruction Scope
The SKILL.md instructs the agent to use the included script to upload local files, poll tasks, and download outputs — this matches the script. The script uploads local files to https://www.runninghub.cn and downloads returned media. One behavior not called out explicitly in SKILL.md: the script, when not given a CLI key, will attempt to read RUNNINGHUB_API_KEY from the user environment and on Windows will try to read HKCU\Environment via winreg.
Install Mechanism
No install spec (instruction-only with a helper script). Nothing is downloaded during install and no external install URLs are present. Risk surface comes from running the included script, not from a remote installer.
Credentials
The script requires an API key to call RunningHub (accepted via --api-key or RUNNINGHUB_API_KEY). The skill metadata did not declare this required environment variable. The script also probes the Windows registry for the same key, which is unusual and should be documented/justified. No other unrelated credentials are requested.
Persistence & Privilege
The skill does not request always:true, does not modify other skills, and does not persist credentials itself. It runs as an on-demand helper script and behaves as a normal, non-persistent skill.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install runninghub-video
  3. After installation, invoke the skill by name or use /runninghub-video
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of runninghub-video skill for image-to-video generation using RunningHub APIs. - Supports multiple official endpoints: Wan 2.2, Kling v3.0 std, Seedance 2.0 (global/fast), with model-specific quick-start examples. - Handles both public image URLs and local file uploads, including automatic uploading and download of media. - Provides robust polling via /openapi/v2/query and immediate download of finished video files. - Includes troubleshooting advice, tuning parameters, and command templates for typical workflows.
Metadata
Slug runninghub-video
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is runninghub-video?

Use RunningHub official standard-model APIs for image-to-video generation. Trigger when the user asks to use RunningHub, 可灵, Seedance, 万相, or other RunningHu... It is an AI Agent Skill for Claude Code / OpenClaw, with 52 downloads so far.

How do I install runninghub-video?

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

Is runninghub-video free?

Yes, runninghub-video is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does runninghub-video support?

runninghub-video is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created runninghub-video?

It is built and maintained by balckbeeai (@darker314159); the current version is v1.0.0.

💬 Comments