kustomer
Warn
Audited by Snyk on Mar 13, 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.md explicitly instructs the agent to fetch and read user-generated Kustomer data (e.g., "List Messages", "Get Message by ID" and conversation-related actions via the Membrane proxy) so untrusted customer messages/conversations could be interpreted and influence subsequent tool actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata