mcp-context7

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 is to query “Context7 MCP tools” for framework/library docs and then summarize findings; if those MCP tools fetch public web/framework documentation at runtime, that would be outsider-authored free text entering the agent’s LLM context via the MCP tool outputs.