k8s-rollouts

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides standard documentation and tool patterns for managing Kubernetes resources using Argo Rollouts and Flagger. All tool calls (such as get_rollout_status and promote_rollout) align with the stated purpose of progressive delivery management.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection as it processes data from external sources (Kubernetes cluster status and analysis runs).
  • Ingestion points: The agent reads data from the cluster using tools such as get_rollout_status, get_analysis_runs, and get_rollout in SKILL.md.
  • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the fetched Kubernetes resource data.
  • Capability inventory: The skill possesses the capability to modify the cluster environment via kubectl_apply, promote_rollout, abort_rollout, and retry_rollout.
  • Sanitization: No explicit sanitization or validation of the data retrieved from the Kubernetes API is performed before it is used to inform deployment decisions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 06:52 PM