v2ex

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

• Third-party content exposure detected (high risk: 0.90). The skill directly fetches user-generated content from the public V2EX forum (e.g., GET https://www.v2ex.com/api/topics/hot.json, GET /topics/:topic_id and GET /topics/:topic_id/replies), so the agent would read and interpret untrusted third-party posts/comments as part of its workflow.