The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill utilizes the scene_description input to construct prompts for image and video generation tasks in Phase A and Phase B.
Ingestion points: The scene_description parameter defined in the inputs section of SKILL.md.
Boundary markers: Absent. The user input is interpolated directly into the prompt string without delimiters or instructions to prevent the model from following commands embedded in the text.
Capability inventory: The skill uses muapi CLI tools and curl to process these prompts and generate media files.
Sanitization: None detected. The input is passed directly to the generative models.
[COMMAND_EXECUTION]: The skill instructions direct the agent to execute specific shell commands using the muapi CLI, such as muapi image edit and muapi video from-image.
[EXTERNAL_DOWNLOADS]: The skill performs network operations using curl to communicate with the api.muapi.ai endpoint for its core functionality, particularly as a fallback for the CLI.

muapi-product-video-ad-maker