agent-orchestration-planner

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly includes a "search_web" tool in TOOL_ORDER and executes tools whose results are appended to the agent's memory/state (see Agent.run memory append and AgentState.add_tool_result), meaning results from open web searches or external APIs would be ingested and read by the agent, exposing it to untrusted third-party content.