The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides numerous curl command examples in the documentation to demonstrate API interactions for asset generation. These commands are intended for manual or agent-driven use and do not involve piped execution or unsafe system modifications.
[EXTERNAL_DOWNLOADS]: The skill references several external resources under the eachlabs.run and eachlabs.ai domains for API endpoints and asset storage. These are vendor-owned resources consistent with the skill's stated purpose of providing 3D model generation services.
[INDIRECT_PROMPT_INJECTION]: The skill functions as a wrapper for generative AI and presents a surface for processing untrusted data.
Ingestion points: User-provided text prompts in the messages field and external image links in the image_urls field serve as data ingestion points in the SKILL.md file.
Boundary markers: The instructions do not define specific delimiters or instructions to prevent the processing of potentially malicious instructions embedded in the input data.
Capability inventory: The skill facilitates network requests to the EachLabs API service for model generation.
Sanitization: There are no mentioned mechanisms for sanitizing user-supplied text or validating the safety of external image URLs before processing.

3d-model-generation