configure

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly configures and can enable the Tavily MCP (references/mcp-config.md) and related web-research workflows (web-research-analyst, market-intelligence, web-research-workflow) which perform web search, extraction and crawling of public URLs, so agents will fetch and read untrusted, user-generated third-party content that can influence subsequent actions.