k8s-external-secrets-troubleshooting

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the kubectl CLI to perform its functions. It executes read operations such as kubectl get, kubectl describe, and kubectl logs to gather diagnostic information about ExternalSecrets, SecretStores, and the ESO controller. It also uses mutation commands like kubectl patch and kubectl annotate for testing fixes, though these are guarded by instructions requiring explicit user approval before execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents an indirect injection surface because it processes untrusted data retrieved from the Kubernetes cluster, including resource manifests, event messages, and controller logs. Maliciously crafted resource names or log entries could theoretically influence agent behavior. However, the skill implements strong compensating controls by strictly forbidding the reading of Secret data and mandating human-in-the-loop approval for any changes to the environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 10:57 PM