storybook-mcp-integration

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch and act on external Storybook content — e.g., the "Chromatic Remote Publishing" and "Graceful Degradation" sections require reading published storybooks (https:///mcp) and a public registry ("21st.dev") via list-all-documentation/get-documentation/preview-stories, and those fetched, potentially user-generated docs and stories are parsed and used to decide reuse/generation/testing, so untrusted third-party content can influence agent actions.