ops-customer-success

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

• Third-party content exposure detected (high risk: 0.75). The skill’s required workflow ingests “User Complaints/Feedback Logs” (raw support requests/community feedback) as inputs, which are outsider-authored free text, and then uses them to “extract common pain points” into reports that would be fed into the agent/LLM context.