The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the muapi CLI tool and curl to interact with remote image and video generation services.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-provided inputs that are directly embedded into model prompts.
Ingestion points: Parameters such as product_image, ingredients_description, and brand_colors are sourced from the user and incorporated into the workflow.
Boundary markers: The skill does not implement boundary markers or instructions to the model to ignore potential commands embedded in these user inputs.
Capability inventory: The skill allows for command execution (muapi) and network communication (curl) to the api.muapi.ai domain.
Sanitization: No sanitization, escaping, or validation is performed on the user-supplied text or URLs before they are used in the generation prompts.

muapi-product-showcase-video