rn-wechat-extract

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

• Third-party content exposure detected (high risk: 0.85). The required workflow fetches a WeChat public account article from an outsider-controlled URL at runtime, extracts its HTML body/title/author into Markdown, and then the agent reads that extracted text (via the output file) into the LLM context—an indirect prompt-injection path from outsider-authored free text.