speckle-syntax-automate

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs Automate functions to call AutomationContext.receive_version() to retrieve the triggering version's Base object from the Speckle server (user-published model data) and then reads/filters those objects to drive actions like attach_error_to_objects and mark_run_failed, so it consumes untrusted, user-generated third-party content that can materially influence behavior.