#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended
notasithlord/peerdThe first AI agent harness native to the browser. A browser extension that runs a full agent loop where you already work: it drives your tabs, spins…
santanderai/autoguardrailsAlignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface
qbnasasn/google-tensor-chipsGoogle Tensor Cracks
mondaycom/hatchaCAPTCHA proves you're human. HATCHA proves you're not.
osintnet/osintnet-publicOsintNET is a browser-based OSINT platform for domain intelligence, website risk scanning, SERP discovery, image intelligence and AI image detection.
openpcc/openpccAn open-source framework for verifiably private AI inference
space0blaster/smartmapLLM based map for research, exploration and discovery.
0tsystemspublicrepos/ifritproxyIFRIT is an AI-powered reverse proxy that intercepts incoming requests in real time, classifying each one as legitimate or malicious. Legitimate…
eqtylab/cupcakeA native policy enforcement layer for AI coding agents. Built on OPA/Rego.
linnix-os/linnixeBPF-powered Linux observability with AI incident detection. AGPL-3.0 licensed.
ntanwir10/guardscan100% Free & Open Source • Privacy-First Security Scanning and AI Code Review CLI
mcp-shark/mcp-sharkWireshark-like forensic analysis for Model Context Protocol communications Capture, inspect, and investigate all HTTP requests and responses between…
beelzebub-labs/beelzebubA secure low code deception runtime framework, leveraging AI for System Virtualization.
lycis/cawdogCAWODOG is a proof-of-concept project demonstrating how to protect Python-based AI models deployed on offline industrial machines. Across three…
liadlevy/cve-2024-8309Proof-of-concept demonstrating prompt injection in Langchain's GraphCypherQAChain leading to SQL injection in Neo4j databases. Includes Docker-based…
jpts/cve-2025-23266-pocProof-of-concept exploit for CVE-2025-23266 (NVIDIAScape) targeting NVIDIA AI container runtime. Demonstrates container escape via GPU driver…
fran-cics/exploittensorflowcve-2021-37678TP Seguridad Informática UTN FRBA 2021
gothburz/cve-2024-11040vllm-project vllm version 0.5.2.2 is vulnerable to Denial of Service attacks.
