kubernetes
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill accesses untrusted data from the Kubernetes cluster which could contain malicious instructions designed to manipulate the agent.
- Ingestion points: The
kubectl logs,kubectl get events, andkubectl describecommands listed inSKILL.mdingest external data into the agent context. - Boundary markers: No specific delimiters or instructions to ignore embedded commands within ingested data are present.
- Capability inventory: The skill enables the
Bashtool, which allows the agent to execute system-level commands. - Sanitization: No log filtering or sanitization logic is provided.
- [Command Execution] (SAFE): The skill provides examples for
kubectl execand shell access. While powerful, these capabilities are directly associated with the primary purpose of Kubernetes cluster administration.
Audit Metadata