#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended
owasp/damn-vulnerable-ml-modelIntentionally vulnerable machine learning model for hands-on security training. Explore common ML vulnerabilities, adversarial attacks, and defensive…
silentchainai/silentchainAI-powered vulnerability scanner extension for Burp Suite with multi-provider support (Ollama, OpenAI, Claude, Gemini)
blacksnufkin/litterboxA self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end…
pduggusa/dugganusa-ietfDugganUSA threat-intelligence contributions to the IETF Hackathon — real-world agentic-attack benchmark vectors, CVE-2026-33697 attestation analysis,…
scrapegraphai/scrapegraph-aiPython scraper based on AI
rocketchat/layneA doggo that helps look for security issues in your repositories.
josh-blythe/bordair-detectorTwo-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…
protectai/vulnhuntrZero shot vulnerability discovery using LLMs
projectdiscovery/openriskopenrisk is a tool that generates a risk score based on the results of a Nuclei scan.
owasp/securemlSecureML - Securing and Watermarking AL models
mbrg/power-pwnAn offensive/defense security toolset for discovery, recon and ethical assessment of AI Agents
appsecco/vulnerable-mcp-servers-labA collection of servers which are deliberately vulnerable to learn Pentesting MCP Servers.
sastraadiwiguna-purpleeliteteaming/llamastack-rce-deterministic-supply-chain-exploitation-hardening-framework-cve-2024-50050-LlamaStack-RCE: Deterministic Supply Chain Exploitation & Hardening Framework [CVE-2024-50050] Focus on AI Security Research…
rooobeam/pickle-deserialization-exploit-in-transformersThis study analyzes Python pickle deserialization vulnerabilities, focusing on CVE-2024-3568 in Hugging Face Transformers' TFAutoModel. We reproduce…
inertfluid/sk-cve-2026-26030-labEthical, network-isolated Docker lab reproducing CVE-2026-26030 — Semantic Kernel in-memory vector store filter eval() RCE (patched in 1.39.4)
oligocybersecurity/shelltorchcheckerA tool that checks if a TorchServe instance is vulnerable to CVE-2023-43654
johnnyzhou666/langgrinch-cve-2025-68664-analysisTechnical analysis of the LangChain serialization injection vulnerability CVE-2025-68664.
