conversation-archaeologist
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly uses the conversation_search and recent_chats tools to mine "ALL past Claude conversations" (user-generated, untrusted conversation content) which the agent will read and interpret, creating a clear avenue for indirect prompt injection.
Audit Metadata