halo-cli-moderation-notifications

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly lists commands to fetch and read Halo comments, replies, and notifications (see "Comments", "Replies", and "Notifications" sections), which are user-generated/untrusted third-party content that the agent is expected to read and act on for moderation decisions.