workflow-orchestration

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly includes an "explorer" agent and even an "explorer-web-sonnet" subagent and states in Common Reference that the explorer "WORK Step에서 코드베이스+웹 탐색을 전담" (explorer performs codebase + web exploration), which shows the workflow expects the agent to fetch and read public web content that can influence subsequent task execution.