How do I install the LLM Attacks Security skill?

Run npx skillmds@latest add gmh5225/llm-attacks-security in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is LLM Attacks Security safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with LLM Attacks Security?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is LLM Attacks Security free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published LLM Attacks Security?

gmh5225 (@gmh5225) published this skill. Their other Agent Skills are listed on their SkillMD profile.

LLM Attacks Security by gmh5225 — Agent Skill

Name: LLM Attacks Security
Rating: 4.2 (5 reviews)
Author: gmh5225

File contents

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

LLM01 - Prompt Injection
LLM02 - Insecure Output Handling
LLM03 - Training Data Poisoning
LLM04 - Model Denial of Service
LLM05 - Supply Chain Vulnerabilities
LLM06 - Sensitive Information Disclosure
LLM07 - Insecure Plugin Design
LLM08 - Excessive Agency
LLM09 - Overreliance
LLM10 - Model Theft

Where to Add Links in README

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.

---name: llm-attacks-securitydescription: Guide for LLM security attacks: prompt injection, jailbreaking, data extraction, and where to place resources in README.md.---# LLM Security Attacks## ScopeUse 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 Reference1. LLM01 - Prompt Injection2. LLM02 - Insecure Output Handling3. LLM03 - Training Data Poisoning4. LLM04 - Model Denial of Service5. LLM05 - Supply Chain Vulnerabilities6. LLM06 - Sensitive Information Disclosure7. LLM07 - Insecure Plugin Design8. LLM08 - Excessive Agency9. LLM09 - Overreliance10. LLM10 - Model Theft## Where to Add Links in README- 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`## NotesKeep additions:- AI/LLM security focused- Non-duplicated URLs- Minimal structural changes## Data SourceFor 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.

Frequently asked questions

LLM Attacks Security