Ai Video Gen

End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Replicate models, LumaAI, Runway, and FFmpeg editing.

Install only if you are comfortable sending prompts and narration to cloud AI providers and using paid API keys. Use a virtual environment, keep .env out of version control, avoid sensitive prompts/media, run scripts in a private working directory, and verify provider support before relying on Runway, ElevenLabs, or the missing helper scripts.

Type: OpenClaw Skill Name: ai-video-gen Version: 1.0.0 The OpenClaw AgentSkills skill bundle for AI video generation appears benign. All Python scripts utilize `subprocess.run` with a list of arguments for executing FFmpeg, which is a secure method that mitigates shell injection risks. API keys are loaded from environment variables, and network requests are directed to legitimate AI service providers (OpenAI, Replicate, LumaAI). File system operations are limited to creating output directories and saving generated media, aligning with the skill's stated purpose. No evidence of data exfiltration, persistence mechanisms, obfuscation, or prompt injection attempts in the markdown files was found. The use of `ffmpeg -safe 0` in `images_to_video.py` is noted, but its context within the script (programmatic construction of a file list with absolute paths) does not indicate malicious intent.