kube-agents: Skill for Claude Code

.agents/skills/review-security-k8s-agents-main/SKILL.md

review-security-k8s-agents-main is a skill for Claude Code, Codex from gke-labs/kube-agents. It costs 23 tokens per session (406 once invoked), scanned A, original, Apache-2.0.

A coordinator for reviewing the security of Kubernetes deployments that run AI agents. Kubernetes is a system for deploying and managing containers across machines.

In plain words
What is it for?
Use it to launch specialist reviews, combine their JSON findings, and filter warnings against the workload's actual design and safeguards.
Why use it?
It divides the review into focused checks so risks involving isolation, network access, credentials, prompt attacks, data leaks, and logs can be considered together.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is gke-labs/kube-agents's own configuration. It tells Claude Code and Codex how to work on kube-agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kube-agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gke-labs/kube-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gke-labs/kube-agents/main/.agents/skills/review-security-k8s-agents-main/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gke-labs/kube-agents

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review-security-k8s-agents-main

README.md
[![agentmods](https://agentmods.dev/badge/skills/gke-labs/kube-agents/review-security-k8s-agents-main/github.svg)](https://agentmods.dev/skills/gke-labs/kube-agents/review-security-k8s-agents-main)
Your own site
<a href="https://agentmods.dev/skills/gke-labs/kube-agents/review-security-k8s-agents-main"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/review-security-k8s-agents-main/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-security-k8s-agents-main

Your own site · 80×15
<a href="https://agentmods.dev/skills/gke-labs/kube-agents/review-security-k8s-agents-main"><img src="https://agentmods.dev/badge/skills/gke-labs/kube-agents/review-security-k8s-agents-main.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 406 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00406
Opus 5 $0.00012 $0.00203
Sonnet 5 $0.00005 $0.00081
Haiku 4.5 $0.00002 $0.00041

Measured 13d ago against content hash 8fb3b8cb3fd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-security-k8s-agents-main scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/review-security-k8s-agents-main/SKILL.md · 34 lines

What it actually says

Task

Coordinate AI agent security review sub-agents, gather findings, and produce a summarized JSON report.

Workflow

1. Context Ingestion

Pass project context (from review-security-k8s-understand) to sub-agents.

2. Parallel Reviews

Launch in parallel sub-agents:

  • review-security-k8s-agents-sandbox
  • review-security-k8s-agents-firewall
  • review-security-k8s-agents-credentials
  • review-security-k8s-agents-prompt-injection
  • review-security-k8s-agents-data-exfil
  • review-security-k8s-agents-audit-logs

CRITICAL: Instruct each to output JSON:

[{"agent": "<skill-name>", "findings": [{"message": "<desc>", "file": "<name>", "line": "<num>"}]}]

(Return empty list if no findings). Wait for completion.

3. Triage & Filtering

Evaluate the raw findings against the project context to determine actual risk. Filter out findings that are functionally required by the workload's specific role or adequately mitigated by broader architectural controls.

  • Example: Filter out missing egress proxy warnings if the agent's execution sandbox is completely air-gapped and the main control loop is strictly allowlisted to a single LLM API.
  • Example: Filter out root execution warnings inside the execution sandbox if the context confirms the sandbox utilizes a secure VM-based RuntimeClass (e.g. gVisor or Kata Containers) providing a secure sandbox isolation boundary.

4. Aggregation

Merge the filtered findings into a single JSON array. Output MUST be valid JSON string (markdown blocks okay). Omit agents with no findings or return empty findings.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 34 lines · 23 tokens per session scan A 8fb3b8cb3fd1

Subscribe to this mod's changes

review-security-k8s-agents-main is a skill published in the GitHub repository gke-labs/kube-agents (54 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 406 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

compute-env-setup

Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.

companion-inc/feynman · 45 tokens

securing-kubernetes-on-cloud

This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…

xalgorix/xalgorix · 80 tokens

detecting-privilege-escalation-in-kubernetes-pods

Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.

xalgorix/xalgorix · 40 tokens

implementing-rbac-hardening-for-kubernetes

Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.

xalgorix/xalgorix · 41 tokens

docker-socket-mount

Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.

PurpleAILAB/Decepticon · 67 tokens