

Lightweight Agent Detection & Response (ADR) layer for AI agents — guards commands, files, and web requests. Part of Gen Agent Trust Hub.

Anti-LLM obfuscation via finger counting

OWASP Secure Agent Playbook Project

NOVA - Claude Code Protection System against prompt injection attacks

Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)

Finding vulnerabilities through dumb brute force

The system of record for AI-written software. A persistent graph of entities, relationships, changes, and provenance, so humans and AI agents see…

A doggo that helps look for security issues in your repositories.

A TypeScript package that provides AI-powered agents for Application Security (AppSec) tasks, built on top of the frontier models.

Demo showing Claude Opus does not find CVE-2023-0266

[NeurIPS '25] Code for Paper "IF-Guide: Influence Function-Guided Suppression of Harmful Training Data for Reducing LLM Toxicity"

The vibe-coding security sentinel. Apache-2.0 agentic security toolkit for AI-assisted projects: 5 deterministic scouts + LLM Brain Layer (BYOK…

Host-agnostic pre-write security hook for coding agent: detects user-input patterns via Semgrep and emits deterministic, no-LLM security guidance.

CVE-2026-67598 — Emlog Pro: disabled TLS certificate validation in AI assistant (MITM → API-key theft). CWE-295, CVSS 9.1. Reported by @IlhomjonR.

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

Silent dependency injection through AI documentation pipelines. 240 isolated Docker runs proving Context Hub's zero-sanitization MCP server lets…