space-wechat-layout

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested into the LLM context via the user-provided “article” content (the operating user pastes it, but it is not authored by the agent/system), which the workflow then transforms and embeds into the runtime HTML preview.