mcp-server-integration

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

• Third-party content exposure detected (high risk: 0.70). The skill’s required workflow is to configure/register MCP servers and tools, which at runtime typically involves ingesting MCP server-provided content (e.g., tool descriptions/capabilities and responses) into the agent’s LLM context; since MCP servers are external parties, this is outsider-authored free text via the MCP tool/metadata exchange path.