← 返回 Skills 市场
volcengine-video-generate
作者
volcengine_skills
· GitHub ↗
· v1.0.0
955
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install volcengine-video-generate
功能描述
Using volcengine video_generate.py script to generate video, need to provide filename and prompt, optional provide first frame image (URL or local path).
安全使用建议
This skill appears to be a simple wrapper over Volcengine's Ark content-generation API and downloads the resulting video, which aligns with its stated purpose. However: (1) the registry lists no required environment variables but the script needs an API key (MODEL_VIDEO_API_KEY or ARK_API_KEY) — be prepared to provide a valid key before running; (2) SKILL.md claims an additional fallback using VOLCENGINE_ACCESS_KEY and VOLCENGINE_SECRET_KEY, but that logic is not present in the code — treat that claim as inaccurate; (3) the script will send your text prompt and any provided image (it may convert a local image to a base64 data URI) to the Ark API and will download the returned video URL — only use with a trusted API endpoint and avoid embedding secrets in prompts or image metadata; (4) source and homepage are unknown — if you need stronger assurance, request provenance (author, official repo, or signed release) or run the script in an isolated environment. If you accept these caveats and can supply the required API key, the skill is usable; otherwise proceed cautiously or seek a version with clearer credential handling and provenance.
功能分析
Type: OpenClaw Skill
Name: volcengine-video-generate
Version: 1.0.0
The `scripts/video_generate.py` script exhibits risky capabilities by allowing the reading of arbitrary local files (via the `first_frame_image` argument) and sending their base64 encoded content to the Volcengine API. Additionally, it permits writing the generated video to an arbitrary local path (via the `filename` argument), including creating directories. While these actions are plausibly needed for the skill's stated purpose (using local images and saving videos locally), they introduce a significant risk of data exfiltration or arbitrary file writes if an attacker can manipulate the input arguments, for example, through prompt injection against the executing agent.
能力评估
Purpose & Capability
The code (scripts/video_generate.py) implements text-to-video generation via the Ark SDK and downloads the produced video to the requested filename — this matches the skill name/description. Minor mismatch: SKILL.md claims a fallback to use VOLCENGINE_ACCESS_KEY/VOLCENGINE_SECRET_KEY to obtain an Ark API key, but the included script only reads MODEL_VIDEO_API_KEY or ARK_API_KEY; there is no implementation of the described fallback.
Instruction Scope
Instructions are narrowly scoped to running the script with filename, prompt, and optional first-frame image (URL or local path). They correctly describe local file reading (converted to base64) and downloading the generated video. However, SKILL.md documents credential fallback behavior that is not present in the script, which is an instruction/content mismatch.
Install Mechanism
No install spec — instruction-only with a single included Python script. Nothing is downloaded or installed by the skill itself, which is low-risk from an install mechanism perspective.
Credentials
Registry metadata declares no required environment variables, but both SKILL.md and the script rely on sensitive environment variables (MODEL_VIDEO_API_KEY or ARK_API_KEY). SKILL.md also mentions VOLCENGINE_ACCESS_KEY and VOLCENGINE_SECRET_KEY fallback which the script does not implement — this discrepancy is concerning because sensitive credentials are involved but not declared in the metadata. The script will send prompts and optionally base64-encoded image data to the Ark service, which is expected but should be explicit in the metadata.
Persistence & Privilege
The skill does not request permanent presence (always is false), does not modify other skill configs, and does not require elevated system privileges. It will create directories matching the provided filename path and write the downloaded video file, which is expected behavior.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install volcengine-video-generate - 安装完成后,直接呼叫该 Skill 的名称或使用
/volcengine-video-generate触发 - 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
v1.0.0
Initial release of volcengine-video-generate skill.
- Generate videos from text prompts, with optional control over the first frame via image URL or local path.
- Outputs the generated video URL and downloads the file automatically.
- Supports API key environment variables for authentication.
- Provides step-by-step usage instructions and example commands.
元数据
常见问题
volcengine-video-generate 是什么?
Using volcengine video_generate.py script to generate video, need to provide filename and prompt, optional provide first frame image (URL or local path). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 955 次。
如何安装 volcengine-video-generate?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install volcengine-video-generate」即可一键安装,无需额外配置。
volcengine-video-generate 是免费的吗?
是的,volcengine-video-generate 完全免费(开源免费),可自由下载、安装和使用。
volcengine-video-generate 支持哪些平台?
volcengine-video-generate 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 volcengine-video-generate?
由 volcengine_skills(@warm-wm)开发并维护,当前版本 v1.0.0。
推荐 Skills