qiita

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

• Third-party content exposure detected (high risk: 0.80). This skill calls the public Qiita API (e.g., GET /items, /items/{id}, /items/{id}/comments, /tags, /users/{id}) and reads/searches/presents user-generated articles, comments, and tags from an open third-party site, which are untrusted and consumed as part of the agent's workflow.