parallels-discord-roundtrip

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly sends and reads messages in a Discord guild/channel (see SKILL.md entries "guest message send to Discord" and "host sees that message on Discord" plus required Discord guild/channel IDs and bot token), meaning it ingests untrusted, user-generated third‑party content that can affect pass/fail decisions and subsequent actions.