The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill takes user input via the display_text parameter and interpolates it directly into the prompt for the ideogram-v3-t2i model. The lack of sanitization or boundary markers creates an attack surface where a user could provide malicious text to influence the image generation process.
Ingestion points: The display_text input variable in SKILL.md is the primary ingestion point for untrusted data.
Boundary markers: There are no delimiters or explicit instructions to the agent to treat the user input as data rather than instructions.
Capability inventory: The skill has the capability to execute shell commands via the muapi CLI and curl to interact with external APIs.
Sanitization: No filtering, escaping, or validation is performed on the user input before it is used in the prompt template.
[COMMAND_EXECUTION]: The skill uses the muapi CLI tool for image generation tasks. It also provides a curl command template for interacting with the api.muapi.ai API service, which includes the use of the MUAPI_API_KEY environment variable.

muapi-keyboard-art-maker