slack

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly includes a readMessages action that fetches Slack channel messages (user-generated, untrusted content) which the agent is expected to read and could use to decide/send/edit/pin/delete messages, creating a clear avenue for indirect prompt injection from third-party Slack content.