speckle-agents-model-coordinator

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

• Third-party content exposure detected (high risk: 0.70). The skill's workflows and examples (e.g., examples.md "Automated Quality Check Pipeline" pseudocode that calls automation_context.receive_version() and the templates that instruct using a Speckle Receive component with a project/model URL) explicitly require fetching and interpreting user-hosted Speckle project/model data (user-generated/untrusted content) and using that data to make decisions (report run status, trigger actions), which enables indirect prompt-injection risk.