#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended
unknownhl/deepguardCode for ACL 2026 (main) paper "DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation"
kuro0911/cs5446-projectCode repository for CS5446 project exploring defenses against jailbreak attacks on large-language models it includes datasets, notebooks,…
skrkcb2/cve-2024-5452Detailed technical analysis of CVE-2024-5452, a remote code execution vulnerability in PyTorch Lightning via DeepDiff delta property pollution, with…
wang-yanting/agentwatcherCausal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…
vinsontang1/dcvdThe code in "DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization"
vinsontang1/vultriageThe code of VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection
aetherai3/aether-protocol-pWorking implementation: cryptographically verified short-lived identities for AI decision authentication — CVE-2025-59536 (Patent Pending US…
renweimeng/vlun-agent-xVulnAgent-X: A Layered Agentic Framework for Repository-Level Vulnerability Detection
ny1024/clawguardModular security toolkit for autonomous agents providing static analysis, configuration auditing, runtime monitoring, and supply chain verification…
zjuicsr/deeptrapSecurity benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…
blakeblackshear/frigateNVR with realtime local object detection for IP cameras
oscerd/cve-2026-49042PoC reproducer for CVE-2026-49042 (Apache Camel camel-langchain4j-tools): a prompt-injected LLM's tool-call arguments become unfiltered Exchange…
roxanne_ardary/securekitSecurekit is a protocol-agnostic security kernel that enforces zero-trust, sandboxed execution for AI tool use. It sits between any LLM or agent…
maverickaayush/onusLocally-hosted, air-gapped VAPT platform that runs 8 parallel scanning modules, deterministically scores findings with CVSS v3.1, and generates PDF…
owasp/ai-vulnerabilities-playgroundHands-on AI security lab platform with 50+ scenarios across prompt injection, agentic system exploitation, model manipulation, and MCP trust boundary…
owasp/agent-security-regression-harnessExecutable security regression testing for agentic applications and MCP-integrated systems.
owasp/aisvsThe AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…
