content-planning

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 (Step 4: "Research Trending Topics") explicitly directs checking Xiaohongshu's "Explore" page, reviewing competitor top posts, and noting rising hashtags — i.e., ingesting public, user-generated social media content that the agent would read and use to influence planning decisions, which could enable indirect prompt injection.