speckle-impl-federation

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and references/examples.md show workflows that load and process external Speckle project models (e.g., "Load component → load architecture model", GraphQL queries, and SpeckleClient/Power BI connector examples fetching model URLs) — i.e., arbitrary user-generated Speckle project content is fetched and interpreted at runtime and can directly affect tool actions and decision-making.