Break your AI before they do.
-
Updated
Jun 18, 2026 - MDX
#
ai-security-testing
Here are 13 public repositories matching this topic...
PromptMe is an educational project that showcases security vulnerabilities in large language models (LLMs) and their web integrations. It includes 10 hands-on challenges inspired by the OWASP LLM Top 10, demonstrating how these vulnerabilities can be discovered and exploited in real-world scenarios.
owasp vulnerable-application owasp-top-10 ai-security llm prompt-injection vulnerable-llm-application ai-security-testing prompt-injection-llm-security prompt-injection-defense llm-red-teaming llm-top10
-
Updated
Jun 29, 2025 - Python
Curated AI security and safety evaluation benchmarks well-regarded by Frontier AI labs
-
Updated
May 17, 2026
AI Coding Hackathon Project - Experimenting with AI-assisted development workflows
rust hackathon ai-security ai-security-testing ai-security-tool ai-coding claude-code ai-coding-assistant codex-cli ai-coding-agent
-
Updated
Oct 18, 2025 - Rust
Ultra-fast AI reverse proxy with semantic cache, PII masking, budget controls, and smart failover — featuring a stunning TUI dashboard
golang open-source reverse-proxy openai ai-security anthropic semantic-cache llm-proxy ai-security-testing gimini ai-security-tool ai-security-tools ai-security-toolkit
-
Updated
Jul 6, 2026 - Go
Research and defense implementation for prompt injection vulnerabilities in LLM applications
python owasp cybersecurity owasp-top-10 ai-security prompt-injection llm-security ai-security-testing secureflag
-
Updated
Oct 17, 2025 - Python
Secure your code in seconds. VibeSafe is an AI-native DevSecOps CLI tool that detects vulnerabilities, secrets, insecure configs, and hallucinated dependencies before they ship.
npm-package vulnerability-detection vulnerability-scanners secure-coding devsecops cli-tool ai-security open-source-security supply-chain-security javascript-security ai-security-testing ai-security-tool secure-install
-
Updated
May 17, 2025 - TypeScript
AI-control research prototype testing fingerprint-aware untrusted LLM policies (within sandboxed model weight-exfiltration tasks) against matched LinuxArena model-registry honeypots under Control Tower's trusted-monitoring blue protocols and matched-decoy telemetry
cybersecurity honeypots control-tower insider-threats ai-control ai-security-testing model-security trusted-monitoring linuxarena weight-exfiltration
-
Updated
Jul 24, 2026 - Python
🛡️ EDR-Hunter Pro - AI-Powered Endpoint Detection & Response platform. Real-time monitoring, anomaly detection, and Telegram Bot alerts.
python linux bot alert dashboard python3 cybersecurity edr ai-security endpoint-security streamlit streamlit-dashboard cybersecurity-tools ai-security-testing ai-security-tool telegram-bot-ai-assistant
-
Updated
Apr 18, 2026 - Python
A Solution to The Gandalf AI from Lakera. https://gandalf.lakera.ai/ The Gandalf LLM README documents the inputs used to reveal secret passwords through various levels of the Gandalf AI by Lakera, with each input tested multiple times for consistency.
-
Updated
May 18, 2024
OWASP Foundation web repository
-
Updated
Jun 1, 2026 - Python
OpenGnosis is a red-teaming framework for evaluating the safety boundaries of LLMs.
ai-security ai-red-team llm-security ai-security-testing llm-red-team ai-red-teaming llm-red-teaming
-
Updated
May 23, 2026 - Python
Improve this page
Add a description, image, and links to the ai-security-testing topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the ai-security-testing topic, visit your repo's landing page and select "manage topics."