ui-designer

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and analyzes arbitrary user-provided reference images (e.g., "Attach reference images to the subagent context" and reading from a user-specified reference-images directory), which are untrusted user-generated/third-party content that the agent is expected to read and interpret.