ai-redteam-lord SKILL.md skillA

ai-redteam-lord from m3taz-ahmed/aizee is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add m3taz-ahmed/aizee/ai-redteam-lord@git:20261027.3620171

Pins git:20261027.3620171 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
m3taz-ahmed/aizee
Path
skills/ai-redteam-lord/SKILL.md
Versions recorded
2
Latest version
git:20261027.3620171, committed Oct 27, 2026
First version recorded
Sep 6, 2026
Size
5,461 bytes
Repository stars
6
License
MIT

Lord skill for CI-integrated AI red-teaming — adversarial testing across prompt injection, jailbreak, data leakage, bias, and tool abuse with measurable coverage and false-positive tracking.

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

# AI Redteam Lord

[OBJ] Integrate automated adversarial testing into CI pipelines to find, measure, and fix AI vulnerabilities before production deployment.

## Problem

AI systems fail in ways traditional security testing does not cover: prompt injection exfiltrates data, jailbreaks bypass guardrails, hallucinated tool calls cause real damage, and bias surfaces in production. Red-teaming is often a one-off manual exercise — it must be continuous, measurable, and gated in CI to keep pace with model and prompt changes.

## Rules

1. [REQ] **Red-team in CI.** Adversarial tests MUST run in CI on every PR touching prompts, system messages, tool definitions, or model config. Use Promptfoo (local/fast), Garak (broad probes), Detoxio (enterprise), Arthur Bench (comparison). No manual-only red-teaming.
2. [REQ] **Attack category coverage.** Test suites MUST cover: prompt injection (direct + indirect), jailbreak ( DAN, role-play, encoding), data leakage (PII extraction, system prompt extraction), hallucination (fabricated facts, fake citations), bias (demographic, sentiment), tool abuse (unauthorized calls, parameter manipulation).
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_cbschlccfo6qex5b/2458bd43e984ed7eb67f9cc5495e52f08e527137bc4e982af6f48813ffdf16cf.json

Then /plugin install ai-redteam-lord@markdownregistry-cbschlccfo6qex5b in Claude Code. It installs git:20261027.3620171, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add m3taz-ahmed/aizee/ai-redteam-lord@sha256:2458bd43e984ed7e

The line at the top of this page pins the label git:20261027.3620171, 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_cbschlccfo6qex5b.svg)](https://markdownregistry.com/a/art_cbschlccfo6qex5b)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in m3taz-ahmed/aizee/ai-redteam-lord since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of ai-redteam-lord from somewhere else? Ask it: where did my ai-redteam-lord come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 2 versions of this file, between Sep 6, 2026 and Oct 27, 2026, about one every 51 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261027.3620171 latest2026-10-27 3620171 5,461 BA view · diff
git:20260906.9629f092026-09-06 9629f09 5,440 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (5461 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

m3taz-ahmed/aizee · 6 stars · license MIT · pushed 2026-11-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cbschlccfo6qex5b
GET https://markdownregistry.com/api/v1/resolve?ref=m3taz-ahmed/aizee/ai-redteam-lord
GET https://markdownregistry.com/api/v1/blob/2458bd43e984ed7eb67f9cc5495e52f08e527137bc4e982af6f48813ffdf16cf

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 m3taz-ahmed/aizee

CLAUDE.md@.claude CLAUDE.md file
m3taz-ahmed/aizee · .claude/CLAUDE.md
git:20261107.4ae71c4 · audit A · 6 stars
global-os SKILL.md skill
m3taz-ahmed/aizee · .claude/skills/global-os/SKILL.md · Load aiZee context layers and route to the correct workflow.
git:20260817.b0f7e30 · audit A · 6 stars
graphify SKILL.md skill
m3taz-ahmed/aizee · .claude/skills/graphify/SKILL.md · Query the graphify knowledge graph before reading files. Trigger /graphify.
git:20260714.353f8b0 · audit A · 6 stars
aizee Cursor rule
m3taz-ahmed/aizee · .cursor/rules/aizee.mdc · aiZee canonical adapter
git:20261107.4ae71c4 · audit A · 6 stars
git Cursor rule
m3taz-ahmed/aizee · .cursor/rules/git.mdc · Git rules. Conventional commits, atomic staging, no force push.
git:20260714.353f8b0 · audit A · 6 stars
graphify Cursor rule
m3taz-ahmed/aizee · .cursor/rules/graphify.mdc · Graphify knowledge graph first. Use before grep/read.
git:20260714.353f8b0 · audit A · 6 stars
mcp Cursor rule
m3taz-ahmed/aizee · .cursor/rules/mcp.mdc · MCP usage. Context7 for docs, graphify for codebase.
git:20260817.b0f7e30 · audit A · 6 stars
memory Cursor rule
m3taz-ahmed/aizee · .cursor/rules/memory.mdc · Memory sync. Read MEMORY.md at start, update after milestone.
git:20260811.7220bad · audit A · 6 stars
quality Cursor rule
m3taz-ahmed/aizee · .cursor/rules/quality.mdc · Code quality. 0 linter warnings, SOLID/DRY/KISS, strict typing.
git:20261006.fcbea87 · audit A · 6 stars
security Cursor rule
m3taz-ahmed/aizee · .cursor/rules/security.mdc · Security rules. Validate inputs, no leaks, no wildcard CORS.
git:20260926.b417e97 · audit A · 6 stars
tech-stack Cursor rule
m3taz-ahmed/aizee · .cursor/rules/tech-stack.mdc · Tech-stack version gating. Detect exact version from lockfile.
git:20260714.353f8b0 · audit A · 6 stars
global-os SKILL.md skill
m3taz-ahmed/aizee · .devin/skills/global-os/SKILL.md · Load aiZee context layers and route to the correct workflow.
git:20260817.b0f7e30 · audit A · 6 stars

Every file in m3taz-ahmed/aizee

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