k8s-rollouts
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (SAFE): The skill processes Kubernetes manifests, which is its primary intended function. While this represents a potential data ingestion surface, it is standard for deployment tools.
- Ingestion points: Manifest strings passed to the
kubectl_applytool in SKILL.md. - Boundary markers: Absent, as standard YAML interpolation is used.
- Capability inventory: Write-access capabilities include
kubectl_apply,rollout_promote_tool, androllout_abort_tool. - Sanitization: Not present within the skill instructions, relying on the underlying Kubernetes API for validation.
Audit Metadata