claudeclaw-group-agent
Warn
Audited by Snyk on May 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly processes and responds to all messages in customer WhatsApp groups (see "Customer group: ALL messages processed", bootstrapOnboardingGroup/group_agent_config) and loads recent turns from claudeclaw_turns into the system prompt via buildMessagesFromHistory(), meaning arbitrary user-generated WhatsApp content is ingested and can materially influence model actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata