figma-to-swiftui

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow ingests outsider-authored free text when it reads a user-provided “source brief, ticket, .md, .txt, or inline product spec” (step 1), which can contain arbitrary text authored by someone other than the operating user; that text is then placed into the agent’s LLM context for extraction.