gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-prompt-injection/SKILL.md

review-security-k8s-agents-prompt-injection skillA

review-security-k8s-agents-prompt-injection is agent-read markdown (skill) from gke-labs/kube-agents: Reviews AI agent architectures (API gateways, WAFs, input sanitization) for prompt injection risks..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add gke-labs/kube-agents/review-security-k8s-agents-prompt-injection@git:20260521.2bcbdef
Exact content
mdr add gke-labs/kube-agents/review-security-k8s-agents-prompt-injection@sha256:38f30c6541731c55

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_hli55ds5jioxvlax.svg)](https://markdownregistry.com/a/art_hli55ds5jioxvlax)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260521.2bcbdef latest2026-05-21 2bcbdef 602 BA view · diff
git:20260521.27b4bc92026-05-21 27b4bc9 619 BA view · diff
git:20260521.94c412d2026-05-21 94c412d 1,085 BA view · diff
git:20260521.6d9669a2026-05-21 6d9669a 1,495 BA view · diff
git:20260520.4daa43e2026-05-20 4daa43e 1,164 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (602 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 · 61 stars · license Apache-2.0 · pushed 2026-09-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hli55ds5jioxvlax
GET https://markdownregistry.com/api/v1/resolve?ref=gke-labs/kube-agents/review-security-k8s-agents-prompt-injection
GET https://markdownregistry.com/api/v1/blob/38f30c6541731c5552ee30ffc21ef76454d2a2ac31a8b43a482b9bd8eff503e4

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.