speckle-impl-revit

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflows explicitly instruct the agent to browse/load user-generated Speckle projects/models (e.g., "Browse to the source Speckle project and model", Speckle web viewer, and "Speckle Model URL"), so the agent would ingest untrusted third‑party model data and properties (displayValue, properties, referencePointTransform) that can materially influence loading/coordination decisions.