The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes the official meshy-cli tool to perform its operations. It specifically instructs the agent to use npm exec --package=meshy-cli@0.4.0 if a local installation is missing, which fetches a pinned version of the vendor's package from the NPM registry.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its core functionality of processing external data.
Ingestion points: The agent ingests untrusted data from user-provided text prompts, image URLs, and external model files when creating or refining 3D assets, as detailed in references/printing.md and references/delivery.md.
Boundary markers: The instructions do not specify the use of delimiters or specific safety warnings to prevent the agent from interpreting instructions that might be embedded within user-supplied text or asset metadata.
Capability inventory: The skill is capable of executing shell commands via the meshy CLI and performing file system write operations within a defined WORKSPACE directory, as described in references/setup.md.
Sanitization: The skill mitigates risks by requiring the use of structured data formats (--format json) and validated schemas (--output-schema v1) for all CLI interactions, which prevents many common injection vectors into the agent's context.

meshy-3d-printing