observability-k8s-investigation

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime queries ingest K8s event and object snapshot text from outsider-authored sources—specifically logs-k8seventsreceiver.otel-* and logs-k8sobjectsreceiver.otel-* where body.text/object fields originate from Kubernetes components and cluster state (not authored by the operating user), which the agent then places into the LLM context via query results.