← Back to Skills Marketplace
video-generation
by
TobeyRebecca
· GitHub ↗
· v1.0.0
· MIT-0
86
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install toby-video-generation
Description
Generate AI videos using SkillBoss API Hub. Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame,...
Usage Guidance
Before installing or using this skill: 1) Inspect seedance.py and confirm the API base URL (PILOT_URL). The docs and code disagree (api.skillbossai.com vs api.heybossai.com); only proceed if you trust the endpoint your API key will contact. 2) Limit the SKILLBOSS_API_KEY permissions if possible and avoid reusing a high-privilege key. 3) Be aware the tool will read local image files and save downloaded videos to disk; do not point it at sensitive directories or root-owned paths. 4) The Feishu upload guide in the package requires separate Feishu credentials (app_id/app_secret/app_access_token) — those are not provided by this skill and should only be supplied if you trust the full upload workflow. 5) If you need higher assurance, ask the publisher for the canonical API host and source (homepage/repo) or run the tool in a restricted environment first. If you cannot resolve the host mismatch, treat the package as untrusted.
Capability Analysis
Type: OpenClaw Skill
Name: toby-video-generation
Version: 1.0.0
The skill bundle contains a shell injection vulnerability in `seedance.py` via the use of `os.system` to open downloaded files on macOS without path sanitization. There is also a discrepancy between the API domain listed in `SKILL.md` (`api.skillbossai.com`) and the one hardcoded in the Python script (`api.heybossai.com`). While the tool's behavior of reading local images and sending them to a remote API is consistent with its stated purpose of AI video generation, the lack of input validation in shell commands and the inconsistent endpoint documentation warrant a suspicious classification.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description, SKILL.md, and seedance.py all indicate a video-generation skill that uses a single SKILLBOSS_API_KEY — that is coherent. HOWEVER the SKILL.md Base URL is 'https://api.skillbossai.com/v1/pilot' while the bundled seedance.py uses PILOT_URL = 'https://api.heybossai.com/v1/pilot' (different host). This discrepancy should be resolved before supplying an API key; it could be a harmless outdated doc or a misconfiguration pointing to an unexpected endpoint.
Instruction Scope
The instructions and CLI operate within the stated domain: they send requests to a /v1/pilot endpoint, accept local images (converting to data: URLs), download generated videos, and optionally instruct using an OpenClaw 'message' tool to upload to Feishu. The docs explicitly show reading local files and uploading via Feishu — expected for the advertised functionality but worth noting because it requires local file access and will cause files to be sent to external services (SkillBoss API and Feishu).
Install Mechanism
No install spec is provided (instruction-only), and the code file is bundled directly. There is no downloading from third-party URLs or package installs in the manifest, so nothing arbitrary will be fetched during install by the skill itself.
Credentials
The skill declares and uses a single SKILLBOSS_API_KEY, which matches its purpose. However the included Feishu integration doc refers to feishu.app_id / feishu.app_secret and an app_access_token (external to this skill). Those Feishu credentials are not required by seedance.py itself but are required if the user follows the 'send via Feishu' guide — users should not assume the SKILLBOSS_API_KEY alone grants Feishu access. Limit API key scope and verify which keys you provide.
Persistence & Privilege
The skill is not marked 'always:true' and is user-invocable only. It does local file reads/writes (saving downloaded videos) but does not request elevated or persistent platform privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install toby-video-generation - After installation, invoke the skill by name or use
/toby-video-generation - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of seedance-video skill for AI video generation via SkillBoss API Hub.
- Supports generating AI videos from text prompts or images (first frame, first+last frame, reference images).
- Access powerful Seedance models: 1.5 Pro (with audio), 1.0 Pro, 1.0 Pro Fast, and 1.0 Lite variants.
- Includes a robust Python CLI tool for easy video creation, error handling, and local image support.
- Allows querying and managing video generation tasks, plus detailed usage examples for both CLI and raw curl.
- Offers advanced customization: video duration, resolution, aspect ratio, and additional model parameters.
Metadata
Frequently Asked Questions
What is video-generation?
Generate AI videos using SkillBoss API Hub. Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame,... It is an AI Agent Skill for Claude Code / OpenClaw, with 86 downloads so far.
How do I install video-generation?
Run "/install toby-video-generation" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is video-generation free?
Yes, video-generation is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does video-generation support?
video-generation is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created video-generation?
It is built and maintained by TobeyRebecca (@tobeyrebecca); the current version is v1.0.0.
More Skills