topic-management

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs navigating to and running a console script on x.com pages (x.com/i/topics and x.com/settings/your_topics), which causes the agent to read and act on public, user-generated topic content from X (a third-party site), so untrusted page content can influence follow/unfollow actions.