k8s-network-policy

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill provides guidance on how to report Kubernetes security states, ensuring that "no policies found" is interpreted correctly as a high-risk default-allow state. These instructions are operational best practices rather than malicious injection attempts.
  • [COMMAND_EXECUTION]: The skill leverages the kubectl binary to perform permission checks and retrieve network policy configurations. This execution is limited to read-only resource enumeration within the scope of the provided kubeconfig.
  • [DATA_EXFILTRATION]: The skill contains no network calls to external domains and explicitly denies access to sensitive Kubernetes secrets, minimizing exfiltration risks.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Kubernetes API (ingestion point: resources_list in SKILL.md). While boundary markers are absent, the risk is minimized by the skill's limited read-only capability and the structured nature of the reported policy rules.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 09:47 AM
Security Audit — agent-trust-hub — k8s-network-policy