kubernetes-operator

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: A comprehensive analysis of the skill's documentation, operation guides, and examples reveals no malicious behavior, credential harvesting, or unauthorized communication. The instructions prioritize best practices like non-root execution and least-privilege RBAC.
  • [NO_CODE]: This skill consists solely of markdown instructions and metadata, containing no Python scripts, Node.js packages, or binary executables.
  • [PROMPT_INJECTION]: The skill is designed to analyze external artifacts such as Kubernetes manifests and Helm charts, which represents a potential surface for indirect prompt injection from untrusted configuration files.
  • Ingestion points: Kubernetes manifests, Helm values, Kustomize overlays, and runtime cluster logs mentioned in SKILL.md.
  • Boundary markers: There are no explicit instructions defining markers to separate analyzed content from the agent's instructions.
  • Capability inventory: The skill provides logic for cluster workload modification and debugging, intended for use with tools that interact with the Kubernetes API.
  • Sanitization: No specific input sanitization or filtering logic is prescribed for the analyzed data artifacts. This risk is inherent to the primary function of auditing infrastructure manifests.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 11:46 AM
Security Audit — agent-trust-hub — kubernetes-operator