mcp-management

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

• Third-party content exposure detected (high risk: 0.90). The skill provisions MCP servers and tools that fetch and browse arbitrary public content (e.g., README and references/configuration.md list server-brave-search and server-fetch, and assets/tools.json includes web-browsing tools such as human-mcp.playwright_screenshot_fullpage, navigate_page, evaluate_script and other URL-taking tools), so the agent can ingest untrusted user-provided or web content that could carry indirect prompt injections.