Ai Video Gen
v1.0.0End-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.
⭐ 6· 5.5k·31 current·33 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The name/description match the code: image generation (OpenAI/Replicate), video generation (LumaAI placeholder), TTS (OpenAI), and FFmpeg-based editing are implemented. The scripts call only the services advertised.
Instruction Scope
SKILL.md directs the agent/user to run the included scripts and to set API keys. However the docs mention additional scripts and folders (multi_scene.py, edit_video.py, examples/) that are referenced but not present in the repository, and there are a few placeholder API flows (LumaAI request structure) that may not match the real provider APIs. These inconsistencies mean the instructions are partially out-of-sync with the code and could cause unexpected runtime behavior.
Install Mechanism
No install spec; this is an instruction + script bundle with a standard requirements.txt. Dependencies are typical (openai, replicate, requests, pillow, python-dotenv) and there are no downloads from arbitrary URLs or archive extraction steps in the manifest.
Credentials
The skill requires several external API keys (OPENAI_API_KEY, REPLICATE_API_TOKEN, LUMAAI_API_KEY, RUNWAY_API_KEY, ELEVENLABS_API_KEY) to perform its advertised functions, which is proportionate. However the registry metadata incorrectly lists 'Required env vars: none' (a mismatch), so the declared metadata under-represents the credential access the code actually needs. This mismatch is a packaging/integrity concern because an installer or automated system could fail to surface required secrets to the user.
Persistence & Privilege
The skill does not request persistent platform privileges (always:false), doesn't write to system-wide configs, and has no install hooks. It runs locally and uses subprocess to invoke FFmpeg (expected for video processing).
What to consider before installing
This package appears to implement what it claims (image→video→TTS→FFmpeg) but the repository and documentation are slightly out-of-sync. Before you install or provide API keys:
- Do not use production or long-lived high-privilege keys. Use limited / test keys and set billing limits where possible. Rotate keys after testing.
- Verify missing files: the README/SKILL.md reference scripts and an examples/ folder that are not present—expect some features to be incomplete or placeholders (LumaAI requests look like a placeholder API flow).
- Inspect the three Python scripts yourself (they are short). They make network calls only to the advertised services and run ffmpeg via subprocess; no obfuscated code or hidden endpoints were found.
- Run the code in an isolated environment (VM or container) with monitoring (network, file writes) if you must test.
- Ensure FFmpeg on your system is the official binary and on PATH to avoid surprises.
If you need higher assurance, ask the publisher for a complete, versioned release (homepage or repo) or request corrected registry metadata (declare required env vars and include the missing scripts/examples).Like a lobster shell, security has layers — review code before you run it.
latestvk973xesx8esf43aw0rm4615vyn805sbb
License
MIT-0
Free to use, modify, and redistribute. No attribution required.