creating-kubernetes-deployments

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides shell scripts in the scripts/ directory that execute kubectl commands to apply, delete, and retrieve the status of Kubernetes resources.
  • [DATA_EXFILTRATION]: The get_resource_status.sh script uses kubectl logs to retrieve pod output. While intended for debugging, this capability can be leveraged to exfiltrate sensitive information if application logs contain credentials or other confidential data.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of external data.
  • Ingestion points: Kubernetes manifests processed by apply_manifest.sh and validate_manifest.sh, and cluster data (logs, events) read by get_resource_status.sh.
  • Boundary markers: Absent; the skill does not use specific delimiters to isolate external content from the agent's instructions.
  • Capability inventory: The skill can execute cluster management actions via the Bash(kubectl:*) tool.
  • Sanitization: The scripts perform YAML syntax and schema validation but do not sanitize natural language content within the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 12:23 AM