ai-security SKILL.md skillA
ai-security from hypnguyen1209/offensive-claude is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hypnguyen1209/offensive-claude/ai-security@git:20260629.9f4a1a5Pins git:20260629.9f4a1a5 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hypnguyen1209/offensive-claude
- Path
skills/ai-security/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260629.9f4a1a5, committed Jun 29, 2026
- First version recorded
- May 19, 2026
- Size
- 10,448 bytes
- Repository stars
- 405
- License
- MIT
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).
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/ML Security ## When to Activate - Red-teaming an LLM/chatbot/copilot for direct & indirect prompt injection and multi-turn jailbreaks. - Testing a RAG pipeline for document/embedding poisoning, embedding inversion, and cross-tenant retrieval leakage. - Auditing an AI agent / MCP server for tool poisoning, excessive agency, and command injection (RCE). - Scanning a model artifact (HuggingFace, `.pt/.pkl/.bin/.gguf`) for deserialization payloads before loading it. - Assessing a model API for extraction/distillation, membership inference, and adversarial-suffix robustness. - Mapping findings to OWASP LLM Top-10 (2025) + MITRE ATLAS for a report. ## Technique Map | Technique | ATT&CK | CWE | Reference | Script | |-----------|--------|-----|-----------|--------| | Direct prompt injection / system-prompt leak (LLM01/LLM07) | T1059.006, T1606 | CWE-1427 | references/prompt-injection-jailbreak.md | scripts/promptinject_harness.py | | Multi-turn jailbreak: Crescendo / Skeleton Key | T1059.006 | CWE-1427 | references/prompt-injection-jailbreak.md | scripts/promptinject_harness.py | …
Read the whole file at its exact version.
How to install
mdr add hypnguyen1209/offensive-claude/ai-security@sha256:a89224ecb71b21ebThe line at the top of this page pins the label git:20260629.9f4a1a5, 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.
[](https://markdownregistry.com/a/art_fyw6sytoyghkfsuf)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between May 19, 2026 and Jun 29, 2026, about one every 10 days. Its first recorded version is graded B and its latest A.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260629.9f4a1a5 latest | 2026-06-29 | 9f4a1a5 | 10,448 B | A | view · diff |
| git:20260629.e082003 | 2026-06-29 | e082003 | 10,572 B | A | view · diff |
| git:20260528.c57f98d | 2026-05-28 | c57f98d | 15,445 B | F | view · diff |
| git:20260528.6136b32 | 2026-05-28 | 6136b32 | 6,402 B | B | view · diff |
| git:20260519.5ae9faf | 2026-05-19 | 5ae9faf | 6,166 B | B | view |
Audit of the latest version
- 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
hypnguyen1209/offensive-claude · 405 stars · license MIT · pushed 2026-10-22 · 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
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 hypnguyen1209/offensive-claude
Every file in hypnguyen1209/offensive-claude