langgraph

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

• Third-party content exposure detected (high risk: 0.90). The skill defines and uses a "search_web" tool and describes a research node that "gathers sources via web search tool" in SKILL.md (Step 3 and Example 2), which clearly fetches and ingests public web content that the agent reads and uses to drive subsequent decisions and actions.