Video Generator | 视频生成器

Automated text-to-video pipeline with multi-provider TTS/ASR support - OpenAI, Azure, Aliyun, Tencent | 多厂商 TTS/ASR 支持的自动化文本转视频系统

This skill is coherent with its purpose, but before installing or running it: 1) Inspect the GitHub repo and the npm package (version 1.6.2, commit hash given) to ensure code matches expectations; 2) Prefer installing/testing inside a sandbox/container or non-production account; 3) Use minimal-scope API keys and monitor billing/usage for the provider you choose (consider creating a separate API key with limited quota); 4) Be aware the installation runs npm install and may create files in ~/openclaw-video/ and run scripts with your user privileges; 5) Verify ffmpeg, node, and other tools are from trusted sources; 6) If you don't want an agent to execute commands autonomously, avoid granting this skill automatic invocation or run it manually after review.

Type: OpenClaw Skill Name: video-generator Version: 1.0.42 The skill bundle describes a legitimate automated text-to-video generation pipeline using Remotion and multiple TTS/ASR providers (OpenAI, Azure, Aliyun, Tencent). While it requires several sensitive API keys, the instructions in SKILL.md and SKILL-EN.md include security best practices such as using .env files with restricted permissions (chmod 600) and advising the agent against hardcoding keys in commands. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the logic is entirely consistent with the stated purpose of video automation.