customer-service-excellence
Warn
Audited by Snyk on Jun 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: 0.95). The required workflow explicitly ingests “the customer’s words (verbatim where possible)” and then mirrors/summarizes them into the agent’s LLM context, which is outsider-authored free text from the customer’s support complaint/channel.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata