shaialon/ai-security-demos
🤯 AI Security EXPOSED! Live Demos Showing Hidden Risks of 🤖 Agentic AI Flows: 💉Prompt Injection, ☣️ Data Poisoning. Watch the recorded session:
This project offers live demonstrations of critical security weaknesses in AI applications, particularly those using AI agents. It takes common AI functionalities, like customer support chatbots and data analysis tools, and shows how malicious inputs or poisoned training data can lead to unauthorized actions, data leaks, or system compromise. The content is designed for cybersecurity professionals, AI product managers, and developers building or deploying AI systems who need to understand and mitigate these risks.
No commits in the last 6 months.
Use this if you are responsible for the security of AI-powered applications and need to see concrete examples of vulnerabilities like prompt injection, data poisoning, and insecure output handling in AI agents.
Not ideal if you are looking for a tool to automatically scan or fix AI security vulnerabilities, as this project provides demonstrations and educational content, not a security solution.
Stars
22
Forks
5
Language
JavaScript
License
MIT
Category
Last pushed
Jul 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/shaialon/ai-security-demos"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
GreyDGL/PentestGPT
Automated Penetration Testing Agentic Framework Powered by Large Language Models
berylliumsec/nebula
AI-powered penetration testing assistant for automating recon, note-taking, and vulnerability analysis.
ipa-lab/hackingBuddyGPT
Helping Ethical Hackers use LLMs in 50 Lines of Code or less..
MorDavid/BruteForceAI
Advanced LLM-powered brute-force tool combining AI intelligence with automated login attacks
mbrg/power-pwn
An offensive/defense security toolset for discovery, recon and ethical assessment of AI Agents