The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides implementation examples using curl to interact with the eachlabs API (eachsense-agent.core.eachlabs.run). These commands are used to transmit prompts for menu design generation and are consistent with the skill's primary function.
[INDIRECT_PROMPT_INJECTION]: The skill processes external inputs which could lead to indirect prompt injection. 1. Ingestion points: User-supplied menu descriptions and reference image URLs. 2. Boundary markers: No delimiters or safety instructions are defined in the command templates to isolate user content. 3. Capability inventory: The skill utilizes curl for network requests and WebFetch for external resource retrieval. 4. Sanitization: No explicit sanitization or validation of the input data is performed before it is sent to the remote API.

menu-design