mmx-h3-video
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing the
mmxcommand-line utility to communicate with video generation services and manage configuration settings. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text prompts and media files, creating a potential surface where malicious instructions embedded in that data could influence the agent's behavior.
- Ingestion points: Untrusted data enters the context via the user's prompt and local file paths passed to flags like
--image,--reference-video, and--reference-audioinSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or warnings to the model to ignore instructions contained within the processed media or prompts.
- Capability inventory: The skill has the ability to execute shell commands (
mmx) and write files to the local filesystem via the--downloadargument. - Sanitization: There is no evidence of content sanitization or validation for the user-supplied prompts or media assets before they are processed by the CLI tool.
- [DYNAMIC_EXECUTION]: The skill includes instructions for building the CLI tool from its source repository using
bun run buildand then executing the resulting JavaScript file withnode. This involves runtime execution of locally generated artifacts, which is a common pattern for developer-focused tools.
Audit Metadata