kubernetes-security-audit

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides informational guidelines and standard kubectl diagnostic commands for auditing cluster security configurations. All commands are standard read-only operations for gathering security metadata.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by ingesting external cluster data (e.g., pod specifications, namespace labels) which could theoretically contain untrusted content. This is a standard risk for auditing tools and is documented here for completeness.
  • Ingestion points: Kubernetes API object metadata retrieved via kubectl get -o json commands (SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: Shell command execution for kubectl queries.
  • Sanitization: None identified; the skill relies on the agent's interpretation of diagnostic JSON output.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 06:29 AM
Security Audit — agent-trust-hub — kubernetes-security-audit