prodsec-skills-ge-core

prodsec-skills-ge-core is a plugin for Claude Code from RedHatProductSecurity/prodsec-skills. Its manifest loads nothing; the 12 skills it bundles cost 526 tokens per session together, scanned A, original, Apache-2.0.

A curated set of 12 security guides for developers and AI coding assistants. It covers areas including injection defense, secrets, containers, Kubernetes and OpenShift access, dependencies, authentication, logging, and AI security.

In plain words
What is it for?
Use it when writing or reviewing code and infrastructure that needs secure input handling, dependency checks, secret protection, container hardening, access control, or AI-specific safeguards.
Why use it?
It gathers practical guidance for common security problems in everyday development instead of requiring developers to find separate guidance for each area.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add RedHatProductSecurity/prodsec-skills
agentmods
npx agentmods add plugins/redhatproductsecurity/prodsec-skills/ge-core
Clone the repo
git clone --depth 1 https://github.com/RedHatProductSecurity/prodsec-skills

Made for: Claude Code.

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 prodsec-skills-ge-core

README.md
[![agentmods](https://agentmods.dev/badge/plugins/redhatproductsecurity/prodsec-skills/ge-core.svg)](https://agentmods.dev/plugins/redhatproductsecurity/prodsec-skills/ge-core)
Your own site
<a href="https://agentmods.dev/plugins/redhatproductsecurity/prodsec-skills/ge-core"><img src="https://agentmods.dev/badge/plugins/redhatproductsecurity/prodsec-skills/ge-core.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 12 skills cost 526 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

prodsec-skills-ge-core 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 4d 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.

ge-core/.claude-plugin/plugin.json · 38 lines

What it actually says

{
  "name": "prodsec-skills-ge-core",
  "description": "GE Core — 12 curated security skills for developers writing code daily: injection defense, web application security, secrets detection, container hardening, OpenShift/Kubernetes access control, dependency auditing, authentication, secure-by-design, audit logging, and AI security.",
  "version": "1.0.0",
  "author": {
    "name": "Red Hat Product Security"
  },
  "homepage": "https://github.com/RedHatProductSecurity/prodsec-skills",
  "repository": "https://github.com/RedHatProductSecurity/prodsec-skills",
  "license": "Apache-2.0",
  "keywords": [
    "security",
    "secure-development",
    "injection",
    "secrets-detection",
    "container-hardening",
    "kubernetes",
    "openshift",
    "supply-chain",
    "web-security",
    "ai-security"
  ],
  "skills": [
    "./ai-code-review",
    "./ai-systems-security",
    "./authentication",
    "./container-hardening",
    "./dependency-vulnerability-audit",
    "./input-validation-injection",
    "./logging",
    "./pod-access-control",
    "./scc-security",
    "./secrets-detection-patterns",
    "./secure-by-design",
    "./web-application-security"
  ]
}
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. 4d ago First seen · 38 lines scan A 02a9fa52e042

Subscribe to this mod's changes

prodsec-skills-ge-core is a plugin published in the GitHub repository RedHatProductSecurity/prodsec-skills (52 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.