The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill collects user inputs for room types, design styles, and specific elements, which are then embedded directly into prompts for image generation tools. The absence of boundary markers or input sanitization creates a surface where malicious user input could potentially influence the behavior of the downstream image generation models.
Ingestion points: User-provided inputs defined in the Inputs section of SKILL.md.
Boundary markers: None observed in the prompt templates.
Capability inventory: Shell command execution (muapi CLI), network access via curl to the Muapi API.
Sanitization: No sanitization or validation of the input strings is performed before interpolation.
[COMMAND_EXECUTION]: The skill instructions direct the agent to execute several shell commands to interact with the Muapi service.
Tools: muapi image edit, muapi image generate, muapi auth configure, and muapi predict wait.
Fallback Mechanism: Instructs the use of curl to send POST requests to https://api.muapi.ai/api/v1/ using the $MUAPI_API_KEY environment variable for authentication.

muapi-interior-design