ae-community

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflows (e.g., SKILL.md and references like community-analyzing-theme-comment.md and community-activity-analysis.md) explicitly instruct the agent to call commands that fetch and read public/user-generated content (search_posts, get_post_detail, get_comments_summary, get_hot_topics, get_risk_content), and those fetched posts/comments are then used to generate reports and drive recommendations, so untrusted third-party content could materially influence agent behavior.