service-triage

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (PHASE 5, Step 5.3 "Voice of Customer Integration") explicitly instructs the agent to evaluate social media sentiment monitoring and incorporate review-site feedback (Trustpilot, G2, App Store), which are public, user-generated sources the agent would be expected to read and act on as part of the triage analysis—exposing it to untrusted third-party content that could carry indirect prompt injection.