halo-moderation-notifications

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly instructs the agent to list and inspect user-generated comments and replies (e.g., "halo comment list", "halo comment get comment-abc123", and "halo comment create-reply ...") which means the agent will fetch and interpret untrusted third-party content from Halo comments as part of its workflow and use that content to decide actions like approving, deleting, or replying.