investigate

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly tells the agent to perform WebSearch and "External pattern search" (Phase 2 / "Search Before Building") and even to open an external URL (https://garryslist.org/posts/boil-the-ocean), meaning it fetches and reads public third-party web content that can influence its debugging decisions.