te-community

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and analyzes user-generated community content (e.g., via search_posts, get_post_detail, get_comments_summary, get_livestream_detail and related tools) and the SKILL.md workflows (for example community-analyzing-theme-comment, community-daily-report, and community-hottopic-insight) require reading and interpreting those third-party posts/comments to drive analysis and recommendations, creating a clear avenue for indirect prompt injection.