ai-article

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md Step 2 "搜集资料") mandates using联网搜索 (e.g., web_search) and explicitly pulling public sources including X (Twitter) posts and other open web content, and Step 3 requires building a "引用证据清单" from those external links that the agent must read and use to form conclusions — meaning untrusted, user-generated third-party content is fetched and can materially influence the agent's outputs.