Skills
skills/rohitg00/kubectl-mcp-server/k8s-policy/Gen Agent Trust Hub

k8s-policy

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (HIGH): The skill's prerequisites section instructs the user to download Kubernetes manifests from remote sources that are not on the trusted organization list.\n
  • Evidence: https://github.com/kyverno/kyverno/releases/latest/download/install.yaml in SKILL.md\n
  • Evidence: https://raw.githubusercontent.com/open-policy-agent/gatekeeper/master/deploy/gatekeeper.yaml in SKILL.md\n- REMOTE_CODE_EXECUTION (HIGH): The skill directs the use of kubectl apply -f or kubectl create -f with remote URLs. This pattern effectively downloads and executes external configuration code on the Kubernetes cluster. Since the sources are not trusted, this allows for potential cluster compromise.\n- PROMPT_INJECTION (LOW): The skill possesses a surface for indirect prompt injection by ingesting and displaying data from cluster policies and audit reports.\n
  • Ingestion points: kyverno_clusterpolicy_get_tool, kyverno_policyreports_list_tool in SKILL.md\n
  • Boundary markers: Absent\n
  • Capability inventory: kubectl_apply allows modifications to the cluster\n
  • Sanitization: Absent
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 06:35 PM