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
mdr add snailsploit/claude-red/offensive-ai-security@git:20260506.70e0c89mdr add snailsploit/claude-red/offensive-ai-security@sha256:345b920695dabd22Pin 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.
[](https://markdownregistry.com/a/art_mffad4wl6iqse7up)
1 badge views in 30 days
Versions
Audit of the latest version
- 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
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
Every file in snailsploit/claude-red