foundations-grounding-communication

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

• Third-party content exposure detected (low risk: 0.10). The skill is a general grounding/communication protocol and at runtime only consumes the user/orchestrator-provided handoff/brief text the workflow is designing for (e.g., “User → agent at session start” / “Brief-to-subagent handoff”), rather than reading outsider-authored free text from an external feed/queue without selection.