hypnguyen1209/offensive-claude · skills/ai-security/SKILL.md

ai-security skillA

ai-security is agent-read markdown (skill) from hypnguyen1209/offensive-claude: Use when attacking an AI/ML system or model — prompt injection & jailbreaks (Crescendo, Skeleton Key, Best-of-N), RAG/vector poisoning, agentic/MCP exploitation (CVE-2025-54136), ML supply-chain RCE (pickle CVE-2025-32434), model extraction / membership inference / adversarial suffixes (GCG).

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 hypnguyen1209/offensive-claude/ai-security@git:20260629.9f4a1a5
Exact content
mdr add hypnguyen1209/offensive-claude/ai-security@sha256:a89224ecb71b21eb

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_fyw6sytoyghkfsuf.svg)](https://markdownregistry.com/a/art_fyw6sytoyghkfsuf)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260629.9f4a1a5 latest2026-06-29 9f4a1a5 10,448 BA view · diff
git:20260629.e0820032026-06-29 e082003 10,572 BA view · diff
git:20260528.c57f98d2026-05-28 c57f98d 15,445 BF view · diff
git:20260528.6136b322026-05-28 6136b32 6,402 BB view · diff
git:20260519.5ae9faf2026-05-19 5ae9faf 6,166 BB 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 (10448 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

hypnguyen1209/offensive-claude · 367 stars · license MIT · pushed 2026-09-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_fyw6sytoyghkfsuf
GET https://markdownregistry.com/api/v1/resolve?ref=hypnguyen1209/offensive-claude/ai-security
GET https://markdownregistry.com/api/v1/blob/a89224ecb71b21eb62cf8d38e9cc00b2c484dc29fa83786f3f131c44a258fe09

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