hero-section

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

• Third-party content exposure detected (high risk: 0.90). The skill's pre-flight steps explicitly say "If a Figma URL is provided, pull screenshots and metadata to match the design precisely," and use get_design_context, which requires fetching and interpreting user/third-party Figma content (user-generated/untrusted) as part of the workflow, so external content can influence generation and actions.