discord-chat-summary

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

• Third-party content exposure detected (high risk: 0.90). This skill reads synced Discord messages from local data files (e.g., ./data/{server-dir}/{channel}/messages.md) which contain user-generated, third-party content from Discord that the agent ingests and summarizes, exposing it to potential indirect prompt injection.