meme-creator
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses established tools such as
ffmpeg,yt-dlp, and Chrome (headless mode) for its primary functionality of video processing and image rasterization. - [SAFE]: External dependencies are managed securely via
uvusing inline PEP 723 metadata, referencing well-known packages likeopencv-python-headless,numpy, andpillowfrom official registries. - [SAFE]: Network operations are restricted to asset acquisition (downloading videos from supported platforms and fetching avatars from
unavatar.io) which are essential to the skill's purpose. - [SAFE]: The 'Asset binding' workflow (asset-binding.md) explicitly includes identity disambiguation steps, which serves as a safeguard against misidentifying entities when fetching external logos or avatars.
- [SAFE]: No patterns of prompt injection, obfuscation, or persistence mechanisms were detected in the instructions or the accompanying scripts.
Audit Metadata