review-adversarial SKILL.md skillA

review-adversarial from gke-labs/kube-agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add gke-labs/kube-agents/review-adversarial@git:20261023.b413863

Pins git:20261023.b413863 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
gke-labs/kube-agents
Path
.agents/skills/review-adversarial/SKILL.md
Versions recorded
9
Latest version
git:20261023.b413863, committed Oct 23, 2026
First version recorded
Aug 18, 2026
Size
29,720 bytes
Repository stars
120
License
Apache-2.0

Reviews a change adversarially — establishes what it claims to do, hunts candidates from eleven angles, then re-derives every candidate from source as a hostile second reader and reports only what survives.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Task

Given a diff range, find the defects in it and report only the ones you can defend. This skill is
the review method itself and holds no plumbing: it is run by an author against their own branch
before opening a pull request (the `AGENTS.md` requirement, wrapped by `review-preflight`), and by a
reviewer against a pull request already open (`.claude/commands/pr-review-batch.md`, which wraps it
in the GitHub-side work), and by `kube-agents-bot` as the method for its candidate passes when a
repository nominates it (step 1 says what that reader keeps and what it cannot do).

`review-docs-drift` is the companion pass, not part of this one. Angle H stops at the rules the
diff visibly breaks and at prose the diff makes false — the one hop from a hunk to the sentence it
falsified — and leaves the rest of the documentation question to that skill.

# Procedure

## 1. Run this in a context that did not write the change

If you are the agent that just produced the diff, **do not run the pass in the conversation that
produced it**. [`review-preflight`](../review-preflight/SKILL.md) is how you get a context that did
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add gke-labs/kube-agents/review-adversarial@sha256:e2f4189ffae8ecaa

The line at the top of this page pins the label git:20261023.b413863, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ttakwgzi4jx5wunl.svg)](https://markdownregistry.com/a/art_ttakwgzi4jx5wunl)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 9 versions of this file, between Aug 18, 2026 and Oct 23, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20261023.b413863 latest2026-10-23 b413863 29,720 BA view · diff
git:20261009.c00e4342026-10-09 c00e434 28,459 BA view · diff
git:20260930.8dabe9c2026-09-30 8dabe9c 27,792 BA view · diff
git:20260925.ccaef472026-09-25 ccaef47 25,653 BA view · diff
git:20260916.6d52c6b2026-09-16 6d52c6b 25,389 BA view · diff
git:20260911.efdfd492026-09-11 efdfd49 25,019 BA view · diff
git:20260901.6e769f12026-09-01 6e769f1 19,108 BA view · diff
git:20260820.da26e2b2026-08-20 da26e2b 18,892 BA view · diff
git:20260818.82b18662026-08-18 82b1866 18,010 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (29720 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

gke-labs/kube-agents · 120 stars · license Apache-2.0 · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ttakwgzi4jx5wunl
GET https://markdownregistry.com/api/v1/resolve?ref=gke-labs/kube-agents/review-adversarial
GET https://markdownregistry.com/api/v1/blob/e2f4189ffae8ecaa93d22e69a02881526169fdd93effa0a8d6c32e99a6114e32

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from gke-labs/kube-agents

edit-mirrored-skill SKILL.md skill
gke-labs/kube-agents · .agents/skills/edit-mirrored-skill/SKILL.md · Edit, sync or start mirroring a `gke-*` skill in `agents/platform/skills/` that is copied from google/skills. Use when…
git:20261016.ac3a849 · audit A · 120 stars
install-kube-agents SKILL.md skill
gke-labs/kube-agents · .agents/skills/install-kube-agents/SKILL.md · Install, set up, or deploy kube-agents (the Kubernetes Agentic Harness) and its Platform Agent onto a GKE cluster in a…
git:20261029.4ef8c38 · audit C · 120 stars
review-address-feedback SKILL.md skill
gke-labs/kube-agents · .agents/skills/review-address-feedback/SKILL.md · Address review feedback on an open pull request: triage and fix findings, reply in every thread, resolve the addressed…
git:20261023.631dcf4 · audit A · 120 stars
review-docs-drift SKILL.md skill
gke-labs/kube-agents · .agents/skills/review-docs-drift/SKILL.md · Reviews a pull request for documentation drift — finds which docs the change should have updated, verifies doc claims…
git:20261030.59401a3 · audit A · 120 stars
review-preflight SKILL.md skill
gke-labs/kube-agents · .agents/skills/review-preflight/SKILL.md · Runs the review passes required before a pull request is opened — adversarial and docs-drift — each in a context that…
git:20261027.d053bac · audit A · 120 stars
review-security-k8s-admission SKILL.md skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-admission/SKILL.md · Reviews Kubernetes Admission Control (Webhooks, VAP/MAP) for vulnerabilities.
git:20260522.4bbd4a0 · audit A · 120 stars
review-security-k8s-agents-audit-logs SKILL.md skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-audit-logs/SKILL.md · Reviews Kubernetes and application audit logging for AI agents, ensuring tamper-proof observability.
git:20260521.2bcbdef · audit A · 120 stars
review-security-k8s-agents-credentials SKILL.md skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-credentials/SKILL.md · Reviews AI agent Kubernetes configurations for credentials exposed to agents.
git:20260521.2bcbdef · audit A · 120 stars
review-security-k8s-agents-data-exfil SKILL.md skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-data-exfil/SKILL.md · Reviews Kubernetes configurations to prevent data exfiltration by AI agents.
git:20260521.2bcbdef · audit A · 120 stars
review-security-k8s-agents-firewall SKILL.md skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-firewall/SKILL.md · Reviews Kubernetes network and firewall configurations specifically for AI agent execution sandboxes.
git:20260903.799c7e3 · audit A · 120 stars
review-security-k8s-agents-main SKILL.md skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-main/SKILL.md · Orchestrates comprehensive Kubernetes security audits specifically tailored for AI agent workloads.
git:20260522.4bbd4a0 · audit A · 120 stars
review-security-k8s-agents-prompt-injection SKILL.md skill
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-prompt-injection/SKILL.md · Reviews AI agent architectures (API gateways, WAFs, input sanitization) for prompt injection risks.
git:20260521.2bcbdef · audit A · 120 stars

Every file in gke-labs/kube-agents

Browse by kind, by grade A, or by owner.