create-3d-model-from-image

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). Runtime path: create_model_from_image ingests image_url/texture_image_url (public URLs or data URIs) and the service will fetch/read that external image content as input, which is outsider-authored free-form content from arbitrary URLs.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs agents to fetch live schema and instructions at runtime from the AgentPMT MCP endpoint (https://api.agentpmt.com/mcp/), and it states that the returned schema/instructions are authoritative and should be applied, meaning remote content can directly control agent prompts/behavior.