The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes several user-controlled input fields which are directly interpolated into prompts for image generation models.
Ingestion points: User inputs room_type, design_style, color_palette, and specific_elements defined in the Inputs section of SKILL.md.
Boundary markers: The instructions do not define any delimiters (like XML tags or triple quotes) or specific guardrail instructions to prevent the model from following commands hidden within the user's design descriptions.
Capability inventory: The skill uses the muapi CLI and curl for network requests to generate images and videos based on these prompts (found in SKILL.md).
Sanitization: There is no evidence of input validation, filtering, or escaping of the user-provided text before it is inserted into the API payloads.
[COMMAND_EXECUTION]: The instructions for the executing agent in SKILL.md explicitly direct the agent to run shell commands using the muapi CLI and curl. While this is the intended operation of the skill to interface with the api.muapi.ai service, it involves executing external processes with parameters derived from user input.

muapi-interior-design