israeli-customer-support-automator

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly instructs monitoring and handling public social media posts (e.g., SKILL.md Step 6 "Monitor brand mentions using social listening tools", the Step 4 escalation trigger "Social media complaint (public) -> L3", and Example 3 describing a Facebook complaint), which means the agent is expected to ingest untrusted, user-generated third-party content and let it drive escalations and actions.