muapi-jewelry-product-video
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined inputs (
jewelry_descriptionandsurface_description) which are directly interpolated into the prompts for image and video generation tools. - Ingestion points: Defined in the Inputs section of
SKILL.md. - Boundary markers: There are no delimiters or specific instructions to the agent to treat the user input as data only, increasing the risk of the agent following embedded instructions.
- Capability inventory: The skill utilizes the
muapiCLI andcurlto perform network requests and media generation. - Sanitization: The skill does not implement validation or sanitization for the inputs before using them in shell commands or prompts.
- [COMMAND_EXECUTION]: The instructions require the agent to execute shell commands using the
muapiCLI tool andcurl. This includes passing an API key ($MUAPI_API_KEY) via headers to an external API endpoint (https://api.muapi.ai).
Audit Metadata