gke-upgrades

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and analyzing live data from a Kubernetes environment, which creates a potential surface for indirect prompt injection if malicious instructions are embedded in resource names, events, or metrics.
  • Ingestion points: Multiple commands in references/runbook-template.md and references/troubleshooting.md (e.g., kubectl get pods, kubectl get events, kubectl get --raw /metrics) fetch dynamic content from the cluster into the agent's context.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing the output of these commands.
  • Capability inventory: The skill provides templates for high-privilege operations, including gcloud container clusters upgrade, kubectl delete validatingwebhookconfigurations, and modifying Pod Disruption Budgets, which could be abused if the agent is influenced by malicious input.
  • Sanitization: There is no requirement or guidance for the agent to sanitize or validate the content retrieved from the cluster tools before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:41 AM
Security Audit — agent-trust-hub — gke-upgrades