The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through user-provided inputs.
Ingestion points: premise and style inputs in SKILL.md.
Boundary markers: Absent; inputs are directly embedded in prompt strings.
Capability inventory: Orchestrates image generation via muapi CLI and curl calls.
Sanitization: Absent; input values are used without validation.
[COMMAND_EXECUTION]: The skill utilizes the muapi CLI tool for configuration and predictive tasks, which is standard for interacting with the MuAPI service.
[EXTERNAL_DOWNLOADS]: The skill interacts with the vendor's API endpoint at api.muapi.ai via curl. This communication is legitimate for the service's functionality.

muapi-storyboard