agent-discord

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated Discord content (e.g., SKILL.md's "snapshot --full" and "message list" which return recent messages, references/common-patterns.md and templates/monitor-channel.sh which parse message content and even auto-respond), so untrusted third‑party messages can be read and influence agent actions.