The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute commands using the muapi CLI tool (e.g., muapi image generate, muapi auth configure) and provides a fallback using curl to interact with https://api.muapi.ai/api/v1/ to process user inputs and fetch results.
[EXTERNAL_DOWNLOADS]: The skill depends on the installation and availability of the muapi CLI tool, which is an external dependency required for its core functionality.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates user-controlled text directly into an image generation prompt without sanitization or boundary markers.
Ingestion points: The display_text variable defined in the Inputs section of SKILL.md is the primary ingestion point for untrusted data.
Boundary markers: Absent. The {{display_text}} placeholder is placed directly within the prompt string without any delimiters or instructions to the model to treat the content as data only.
Capability inventory: The skill has the capability to generate images and make network requests via the muapi CLI or curl commands.
Sanitization: Absent. There are no mechanisms described to validate, filter, or sanitize the user-provided display_text before it is interpolated into the executable prompt.

muapi-keyboard-art-maker