kafka-dlq-review

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly samples and inspects arbitrary DLQ messages from Kafka topics using the Lenses MCP execute_sql flow (see "Step 4: Sample DLQ Messages" in SKILL.md), which exposes the agent to untrusted, user-generated message content that the agent is expected to read and which can materially influence its analysis and follow-up actions.