kubectl-basics
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documents standard
kubectlcommands for cluster administration, resource inspection, and container interaction. These operations are consistent with the skill's stated goal of providing kubectl basics.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines workflows that ingest data from a Kubernetes cluster, such as pod names, event logs, and metadata. This data could be manipulated by an attacker who has access to the cluster, potentially influencing the agent's behavior during debugging or management tasks.\n - Ingestion points: Resource names, status wide-output, and logs retrieved through
kubectl get,kubectl logs, andkubectl describe(SKILL.md).\n - Boundary markers: No explicit delimiters are used to wrap data ingested from the cluster.\n
- Capability inventory: Subprocess calls to
kubectlfor resource manipulation and execution within containers.\n - Sanitization: No input sanitization or validation logic is applied to the data fetched from the Kubernetes environment.
Audit Metadata