discord

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly syncs and searches user-generated Discord messages using discord-cli (see SKILL.md Steps 2–4 and references/commands.md), so the agent ingests untrusted third-party content (Discord channels/messages) and uses it to drive analysis and actions, enabling indirect prompt injection risk.