claude-api

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

• Third-party content exposure detected (medium risk: 0.65). This skill’s required workflow can invoke Anthropic server tools web_fetch_20260209/web_search_20260209, whose returned page/article text (outsider-authored web content) is inserted into the LLM context as web_fetch_tool_result/web_search_tool_result content blocks at runtime.