The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, specifically the muapi CLI and curl, using user-provided variables like brand_name and industry. If these inputs are not sanitized by the executing agent, they could potentially be used to inject shell metacharacters for unauthorized command execution.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by ingesting untrusted data and interpolating it into prompts for various image generation models.
Ingestion points: Input variables brand_name, industry, style_preference, color_preference, and mood defined in SKILL.md.
Boundary markers: No delimiters or "ignore embedded instructions" warnings are used when interpolating these variables into the prompts for ideogram-v3-t2i, flux-2-pro, and gpt4o-text-to-image.
Capability inventory: The skill utilizes muapi CLI execution and curl for network operations.
Sanitization: No sanitization, escaping, or validation of user-provided content is performed before interpolation.
[EXTERNAL_DOWNLOADS]: The skill initiates network operations to https://api.muapi.ai/api/v1/ using curl to interact with the service when CLI aliases are unavailable. While functional for the skill's purpose, this targets a domain outside the standard whitelisted sources.

muapi-logo-branding