k8s-grafana-troubleshooting

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses kubectl to inspect the state of the Kubernetes cluster, including retrieving pod statuses, container logs, and resource configurations. It includes a specific command to perform a rollout restart of the Grafana deployment, which is correctly gated by instructions requiring explicit user approval before execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and interprets data from the Kubernetes cluster environment, such as logs and ConfigMaps, which constitutes an attack surface for indirect prompt injection.
  • Ingestion points: Diagnostic data enters the agent context through kubectl logs, kubectl get configmap, and kubectl events across various cluster namespaces.
  • Boundary markers: No explicit delimiters or instruction-bypass warnings are used in the commands to wrap the data being read.
  • Capability inventory: The skill is capable of executing deployment restarts and interactive queries via the Kubernetes API server.
  • Sanitization: The skill does not sanitize the logs or event data, though it contains specific logic to filter out sensitive environment variables like passwords when querying resource specifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 11:23 PM