Runninghub

v1.0.0

RunningHub - 云端 ComfyUI 平台,用于创建 AI 应用和工作流。支持文生图、文生视频、AI 视频合成等。国内版 runninghub.cn,国际版 runninghub.ai。

0· 411·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name/description (RunningHub cloud ComfyUI) match the SKILL.md instructions and the listed API endpoints. Minor discrepancy: the runtime instructions require a RunningHub API key for Authorization, but the skill metadata does not declare any required environment variable or primary credential.
Instruction Scope
SKILL.md only instructs the agent to call the RunningHub API endpoints (run workflows, query tasks, list workflows, get account info). It does not instruct reading local files, accessing unrelated env vars, or sending data to third-party endpoints outside runninghub.cn / runninghub.ai.
Install Mechanism
No install spec and no code files are included (instruction-only). Nothing will be written to disk or executed beyond normal agent network calls.
Credentials
The skill reasonably requires a RunningHub API key to function, but it does not declare any required env vars or primary credential in the metadata. No other secrets or unrelated credentials are requested.
Persistence & Privilege
The skill is not always-enabled and does not request elevated/persistent system privileges or modifications to other skills or global agent config.
Assessment
This skill appears to be a straightforward adapter for the RunningHub API and is instruction-only (no code installs). Before installing or using it: 1) be prepared to provide your RunningHub API key when asked (the skill's metadata didn't declare it), and only supply keys you control; 2) confirm you trust the RunningHub domains (runninghub.cn / runninghub.ai) and their terms—some workflows (e.g., face-swap) have legal/ethical implications; 3) if you prefer the agent to store the API key as an env var, set that up in a secure place and verify the agent's prompts before pasting secrets; 4) if you need additional assurance, ask the skill author to declare required credentials in metadata or provide an installable implementation that you can review.

Like a lobster shell, security has layers — review code before you run it.

latestvk973yf8p23pahgf76bb8ptfyfd82xeba

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments