The Agent Skills Directory

[SAFE]: The skill is a technical guide for using the Meshy 3D API and does not contain malicious code or patterns.\n
Credential Management: The skill explicitly warns against hardcoding the API key and recommends using environment variables or secret managers (Authorization: Bearer $MESHY_API_KEY), which is a security best practice.\n
Network Security: All network operations are directed to api.meshy.ai, which is the official domain for a well-known and legitimate 3D generative service.\n
Execution Safety: The provided curl command examples are standard for API interaction and do not involve piped execution or suspicious remote scripts.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates an agent's ability to process user-provided text and images, which is the primary intended function for 3D generation but inherently involves processing untrusted content.\n
Ingestion points: User-provided prompt, texture_prompt, and image_url fields in the task payloads described in SKILL.md.\n
Boundary markers: No specific delimiters or boundary warnings are provided to separate user input from the rest of the API command structure, which is standard for this type of integration.\n
Capability inventory: The skill allows the agent to make network requests to the meshy.ai API and handle generated asset files.\n
Sanitization: No explicit sanitization or filtering of user input is specified, as the skill focuses on API implementation rather than input validation.

meshy-3d