muapi-media-editing

Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more

This skill appears to implement the advertised muapi.ai editing features, but the package is sloppy: the registry metadata doesn't list the MUAPI_KEY and required binaries (curl, jq, python3, possibly a 'muapi' CLI), and some helper scripts referenced by the code (e.g., ../media/upload.sh, check-result.sh) are not included. Before using: 1) verify and obtain a MUAPI_KEY only if you trust api.muapi.ai; 2) inspect and run the scripts in an isolated environment (container or VM); 3) be aware the scripts will upload any local media you pass (including faces) to the external service — avoid uploading private/sensitive material; 4) note that the key is saved to a .env file in the working dir if you use --add-key; store keys securely and delete .env if undesired; 5) consider contacting the skill author or source to get a完整 package or correct registry metadata and confirm the missing helper scripts and CLI dependency. If you need help checking the muapi.ai domain or sanitizing the package, gather the missing files or a trusted upstream repo and re-run evaluation.

Type: OpenClaw Skill Name: muapi-edit Version: 1.0.0 The skill bundle provides a set of shell scripts to interface with the muapi.ai API for image and video editing tasks like upscaling, face swapping, and lipsyncing. The scripts include standard logic for local file uploads, API job submission via curl, and result polling, with basic input sanitization using python3's json module. While the scripts include a helper function to save the MUAPI_KEY to a local .env file, this is a transparent configuration utility and there is no evidence of data exfiltration, malicious execution, or prompt injection.