designmd-brand-kit

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

• Third-party content exposure detected (high risk: 0.85). The required workflow ingests outsider-authored free text when it “find[s] the official site before analyzing” and then “manually inspect[s] the official site, screenshots, CSS, and page content” (or uses designmd.supply to fetch public site evidence), which the agent reads and uses as LLM context.