llm-attacks-security

llm-attacks-security is a skill for Claude Code from gmh5225/awesome-ai-security. It costs 31 tokens per session (530 once invoked), scanned B, original, MIT.

A guide to security attacks against language models, including prompt injection, jailbreaking, data extraction, and output manipulation. It also covers common risks such as sensitive-information disclosure and unsafe tool use.

In plain words
What is it for?
Use it when analyzing prompt attacks, bypass attempts, attempts to extract private or training data, model manipulation, or risks listed in the OWASP LLM Top 10.
Why use it?
It helps developers recognize ways an AI system can be tricked, exposed, or pushed to produce unsafe results. It provides a shared vocabulary for discussing these weaknesses.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it when analyzing prompt attacks, bypass attempts, attempts to extract private or training data, model manipulation, or risks listed in the OWASP LLM Top 10.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gmh5225/awesome-ai-security/llm-attacks
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add gmh5225/awesome-ai-security --skill llm-attacks
Clone the repo
git clone --depth 1 https://github.com/gmh5225/awesome-ai-security

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for llm-attacks-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/gmh5225/awesome-ai-security/llm-attacks/github.svg)](https://agentmods.dev/skills/gmh5225/awesome-ai-security/llm-attacks)
Your own site
<a href="https://agentmods.dev/skills/gmh5225/awesome-ai-security/llm-attacks"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-ai-security/llm-attacks/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for llm-attacks-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/gmh5225/awesome-ai-security/llm-attacks"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-ai-security/llm-attacks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 530 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.00530
Opus 5 $0.00015 $0.00265
Sonnet 5 $0.00006 $0.00106
Haiku 4.5 $0.00003 $0.00053

Measured 9d ago against content hash 0c99cfc80dd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

llm-attacks-security scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nullifies safety policiesmediumAnti-refusal

"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.

- DAN (Do Anything Now) prompts

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/skills/llm-attacks/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Security Attacks

Scope

Use this skill when working on:

  • Prompt injection attacks and defenses
  • LLM jailbreaking techniques
  • Training data extraction
  • Model output manipulation
  • AI safety bypasses

Common LLM Vulnerabilities (Cheat Sheet)

Prompt Injection

  • Direct injection (user prompt manipulation)
  • Indirect injection (via external data sources)
  • System prompt extraction
  • Role-play attacks
  • Encoding/obfuscation bypasses

Jailbreaking

  • DAN (Do Anything Now) prompts
  • Character roleplay escapes
  • Multi-turn manipulation
  • Token smuggling
  • Crescendo attacks

Data Extraction

  • Training data memorization extraction
  • PII leakage from context
  • System prompt disclosure
  • API key/secret extraction
  • Model architecture probing

Model Manipulation

  • Output steering
  • Hallucination exploitation
  • Bias amplification
  • Harmful content generation

OWASP LLM Top 10 Reference

  1. LLM01 - Prompt Injection
  2. LLM02 - Insecure Output Handling
  3. LLM03 - Training Data Poisoning
  4. LLM04 - Model Denial of Service
  5. LLM05 - Supply Chain Vulnerabilities
  6. LLM06 - Sensitive Information Disclosure
  7. LLM07 - Insecure Plugin Design
  8. LLM08 - Excessive Agency
  9. LLM09 - Overreliance
  10. LLM10 - Model Theft
  • Prompt injection tools/research: AI Security & Attacks → Prompt Injection
  • Jailbreak techniques: AI Security & Attacks → Model Security
  • Data extraction research: AI Security & Attacks → Privacy & Extraction
  • Defense tools: AI Security & Attacks → Model Security
  • CTFs/challenges: AI Security Starter Pack → CTFs / Practice

Notes

Keep additions:

  • AI/LLM security focused
  • Non-duplicated URLs
  • Minimal structural changes

Data Source

For detailed and up-to-date resources, fetch the complete list from:

https://raw.githubusercontent.com/gmh5225/awesome-ai-security/refs/heads/main/README.md

Use this URL to get the latest curated links when you need specific tools, papers, or resources not covered in this skill.

Read the full file on GitHub · 85 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 85 lines · 31 tokens per session scan B 0c99cfc80dd4

Subscribe to this mod's changes

llm-attacks-security is a skill published in the GitHub repository gmh5225/awesome-ai-security (45 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 530 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens