paper-onion

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

• Third-party content exposure detected (high risk: 0.90). The skill's required input processing explicitly accepts "论文 URL（需要 fetch）" and mandates fetching and deeply analyzing the fetched paper content as part of its four-layer workflow and React artifact generation, so untrusted third‑party webpages can be read and influence the agent's decisions and outputs.