rdq-opencode

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

• Third-party content exposure detected (high risk: 0.75). Runtime LLM context can include outsider-authored free text from the operating user’s conversation (user messages themselves are treated as outsider content relative to the skill), which this skill directly ingests and echoes in Phase 1 “回顯使用者說的話”.