cx-ai-center

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow uses cx spans '<DataPrime query>' to read GenAI span payloads—specifically user-authored conversation text from gen_ai.input.messages/gen_ai.output.messages (or gen_ai.prompt.<n>.content/gen_ai.completion.<n>.content)—directly into the LLM when answering “content questions.”