The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user inputs (animal_type, location, clothing, script) and interpolates them directly into prompts for image and video generation models. There are no explicit sanitization steps or boundary markers described, which could allow a user to influence the generated output beyond the intended scope, though the impact is confined to the generated media.
[COMMAND_EXECUTION]: The instructions direct the agent to execute muapi CLI commands and curl requests. These commands are dynamically constructed using user-provided strings. The execution is targeted at the service's official API endpoint (api.muapi.ai) for the purpose of generating the requested content.

muapi-animal-video-generator