discovery-debrief

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

• Third-party content exposure detected (high risk: 0.95). The skill explicitly prompts the operating user to elicit “Who did you talk to? Tell me in free form.” and then uses that free-form customer conversation content for extraction, so outsider-authored text from the customer/prospect flows into the agent’s LLM context at runtime.