happyfox-chat

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly exposes chat transcripts and visitor/offline messages from third-party users via Membrane actions (see "Popular actions" and "List Transcripts / Get Transcript" in SKILL.md), which are untrusted user-generated contents the agent is expected to read and could materially influence subsequent actions.