muapi-ugc-video-factory
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill populates AI prompt templates for image and video generation using user-provided text and image URLs.
- Ingestion points: User-defined inputs
person,product,script, andenvironmentinSKILL.md. - Boundary markers: The instructions lack delimiters or specific guardrail text to prevent the models from interpreting malicious instructions within the user-supplied variables.
- Capability inventory: The skill utilizes shell commands (
muapiCLI), file system access for local uploads, and network capabilities viacurlto the vendor's API. - Sanitization: No input validation or escaping mechanisms are specified for the user-provided content.
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to manage media and interface with the MuAPI platform.
- Evidence: Use of
muapi upload file,muapi image edit, andmuapi predict waitcommands. - [EXTERNAL_DOWNLOADS]: The skill communicates with external servers to process media assets and retrieve results.
- Evidence: Network requests are directed to the vendor's API endpoint at
https://api.muapi.ai/api/v1/and involve uploading local files.
Audit Metadata