discord

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly exposes actions like readMessages and searchMessages that fetch user-generated Discord channel/DM content (untrusted third-party) which the agent is expected to read and can directly influence follow-up actions (sendMessage, edit/delete, moderation), creating risk of indirect prompt injection.