awesome-gpt-security
github.com/cckuailong/awesome-gpt-security ↗A curated list of awesome security tools, experimental case or other interesting things with LLM or GPT.
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me fun resources from awesome-gpt-security"
Installation instructions →What's inside
Cases
- a CTF-like game that teaches how to bypass LLM using language hacksFun
- ai-goatFun
Learn AI security through a series of vulnerable LLM CTF challenges.
- AI-Powered Fuzzing: Breaking the Bug Hunting BarrierExperimental
- A Practical, AI-Generated Phishing PoC With ChatGPTExperimental
- Can We Generate Shellcodes via Natural Language? An Empirical StudyAcademic
- Capturing the Flag with GPT-4Experimental
Tools
- AdversaryGraphAssessment
AI-assisted CTI-to-detection workbench for ATT&CK/ATLAS mapping, IOC enrichment, TTP comparison, and analyst reporting; Malware Analysis mode is WIP.
- Agent Threat Rules (ATR)Detecting
Open detection standard for AI agent threats (prompt injection, tool poisoning, MCP attacks, skill compromise) — Sigma/YARA-style YAML rules. 330 rules across 9 attack categories with full mapping to OWASP Agentic Top 10 (10/10), MITRE ATLAS (100/113), NIST AI RMF (100%), and SAFE-MCP (78/85). 97.1% recall on the garak probe set and 0% false-positive on 53,577 real-world MCP skills. Shipped in production at Cisco AI Defense and Microsoft agent-governance-toolkit. Apache-2.0.
- Armorer GuardDetecting
Local Rust scanner and MCP proxy for AI-agent prompt injection, credential leakage, exfiltration, and risky tool-call arguments before execution.
- audit_gptAudit
Fine-tuning GPT for Smart Contract Auditing
- AuthzAIAudit
An automated tool to test and analyze API endpoints for potential permission model violations using OpenAI structured outputs.
- AutoAuditIntegrated
An LLM for Cyber Security
GPT Security
- agentic_securityStandard
Agentic LLM Vulnerability Scanner
- ai-exploitsBug Bounty
A collection of real world AI/ML exploits for responsibly disclosed vulnerabilities
- ATT&CK for LLM AppsStandard
- Building A Virtual Machine inside ChatGPTBug Bounty
deprecated but interesting
- Chat GPT "DAN" (and other "Jailbreaks")Bypass Security Policy
- ChatGPT Prompts for Bug Bounty & PentestingBypass Security Policy
Showing a sample of 112 resources. View the full list on GitHub →