chaterimo

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and displays user-generated customer conversation transcripts (see "Read Conversation Transcripts" and the GET /api/v1/conversations/{conversation_id}/ endpoint in SKILL.md), so untrusted third-party messages are ingested and could influence agent behavior.