generating-components

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

• Third-party content exposure detected (high risk: 0.80). The skill's mandatory workflow calls mcp__magic__21st_magic_component_inspiration / 21st.dev (see the Agent Workflow and references/21st-dev.md), which fetches public component examples and code from an open third-party site that may contain user-provided/untrusted content the agent must read and use—creating a clear path for indirect prompt injection.