Home / snailsploit / claude-red · Skills/ai/offensive-ai-security/SKILL.md · GitHub

offensive-ai-security skillC

offensive-ai-security is agent-read markdown (skill) from snailsploit/claude-red.

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.

What the file says

# SKILL: AI Pentest

## Metadata
- **Skill Name**: ai-security
- **Folder**: offensive-ai-security
- **Source**: https://github.com/SnailSploit/offensive-checklist/blob/main/ai.md

## Description
AI/LLM security offensive checklist: prompt injection, jailbreaking, model extraction, training data poisoning, adversarial inputs, LLM-assisted attack automation, and AI system reconnaissance. Use when assessing AI/ML systems, red-teaming LLMs, or researching AI attack vectors.

## Trigger Phrases
Use this skill when the conversation involves any of:
`AI security, LLM security, prompt injection, jailbreak, model extraction, training data poisoning, adversarial input, AI red team, ML security, RAG poisoning, AI attack`

## Instructions for Claude

When this skill is active:
1. Load and apply the full methodology below as your operational checklist
2. Follow steps in order unless the user specifies otherwise
3. For each technique, consider applicability to the current target/context
4. Track which checklist items have been completed
5. Suggest next steps based on findings

---

## Full Methodology

# AI Pentest

## Shortcut
…

Read the whole file at its exact version.

How to install

Latest version
mdr add snailsploit/claude-red/offensive-ai-security@git:20260506.70e0c89
Exact content
mdr add snailsploit/claude-red/offensive-ai-security@sha256:345b920695dabd22

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_mffad4wl6iqse7up.svg)](https://markdownregistry.com/a/art_mffad4wl6iqse7up)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260506.70e0c89 latest2026-05-06 70e0c89 39,806 BC view

Audit of the latest version

C  12 of 17 checks passed. Deterministic, no model, same answer every run.
  • fail: Frontmatter block present
  • fail: Frontmatter declares a name
  • fail: Frontmatter declares a description
  • fail: No prompt-injection phrasing (matched: ignore previous instructions)
  • fail: No script tag (matched: <script)
  • pass: Size between 200 bytes and 200 KB (39806 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 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

Source

GitHub

snailsploit/claude-red · 6,831 stars · license MIT · pushed 2026-09-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_mffad4wl6iqse7up
GET https://markdownregistry.com/api/v1/resolve?ref=snailsploit/claude-red/offensive-ai-security
GET https://markdownregistry.com/api/v1/blob/345b920695dabd22392ee623512df78a8862dd30cde507a02c2d31f9139f2595

Your agent 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.

More from snailsploit/claude-red

offensive-active-directory skill
snailsploit/claude-red · Skills/active-directory/offensive-active-directory/SKILL.md · Active Directory attack methodology for internal network red team engagements. Covers reconnaissance (BloodHound…
git:20260506.70e0c89 · audit A · 6,831 stars
offensive-netexec skill
snailsploit/claude-red · Skills/active-directory/offensive-netexec/SKILL.md · Use this skill whenever the user asks about NetExec (nxc) — a network exploitation and post-exploitation tool for…
git:20260913.0458076 · audit A · 6,831 stars
offensive-api-abuse skill
snailsploit/claude-red · Skills/api/offensive-api-abuse/SKILL.md · Advanced API exploitation methodology focused on business logic abuse and sophisticated attack patterns that bypass…
git:20260825.f7a0553 · audit B · 6,831 stars
offensive-api-security skill
snailsploit/claude-red · Skills/api/offensive-api-security/SKILL.md · Comprehensive API security testing methodology covering REST, gRPC, and WebSocket attack surfaces. Addresses the full…
git:20260825.1885f44 · audit C · 6,831 stars
offensive-jwt skill
snailsploit/claude-red · Skills/auth/offensive-jwt/SKILL.md · JWT attack methodology for penetration testers. Covers algorithm confusion (alg:none, RS256→HS256), weak HMAC secret…
git:20260506.70e0c89 · audit A · 6,831 stars
offensive-oauth skill
snailsploit/claude-red · Skills/auth/offensive-oauth/SKILL.md
git:20260506.70e0c89 · audit C · 6,831 stars
offensive-cicd-pipeline skill
snailsploit/claude-red · Skills/cicd/offensive-cicd-pipeline/SKILL.md · Comprehensive CI/CD pipeline exploitation methodology covering GitHub Actions injection vectors (expression injection…
git:20260825.8cffe5d · audit A · 6,831 stars
offensive-cicd-secrets skill
snailsploit/claude-red · Skills/cicd/offensive-cicd-secrets/SKILL.md · Comprehensive secrets extraction methodology targeting CI/CD environments across all major platforms. Covers…
git:20260825.8cffe5d · audit B · 6,831 stars
offensive-cloud skill
snailsploit/claude-red · Skills/cloud/offensive-cloud/SKILL.md · Cloud security attack methodology covering AWS, Azure, and GCP. Includes credential harvesting (IMDS, ~/.aws, env vars…
git:20260506.70e0c89 · audit B · 6,831 stars
offensive-container-escape skill
snailsploit/claude-red · Skills/container/offensive-container-escape/SKILL.md · Container escape and breakout techniques targeting Docker, containerd, and Podman runtimes. Covers privileged container…
git:20260825.8cffe5d · audit A · 6,831 stars
offensive-k8s-attacks skill
snailsploit/claude-red · Skills/container/offensive-k8s-attacks/SKILL.md · Kubernetes cluster attack techniques covering the full attack lifecycle from initial foothold in a pod to cluster-wide…
git:20260825.8cffe5d · audit B · 6,831 stars
offensive-crypto-attacks skill
snailsploit/claude-red · Skills/crypto/offensive-crypto-attacks/SKILL.md · Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world…
git:20260825.8cffe5d · audit A · 6,831 stars

Every file in snailsploit/claude-red

Other files named offensive-ai-security

offensive-ai-security skill
miosa-osa/osa · priv/skills/offensive-ai-security/SKILL.md · AI/LLM security offensive checklist: prompt injection, jailbreaking, model extraction, training data poisoning…
git:20260913.e13b6b8 · audit C · 74 stars

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