dynamo-troubleshoot

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow runs scripts/collect_dynamo_debug_bundle.py, which executes kubectl get/describe/logs against the target namespace and writes the resulting pod descriptions/logs/events (free-form text authored by other cluster components/users) into files and prints summary.json—this text is then available to the agent for LLM context, creating an indirect prompt-injection surface from outsider-authored Kubernetes content.