
BrokenHill
A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)

A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)

AI-driven CLI for testing Android and iOS apps using natural language. Generates, runs, and fixes end-to-end tests on emulators/simulators with…

Android deeplink misconfiguration detector and exploitation tool

Claude Skill that audits your projects for RLS misconfigurations, exposed keys, auth bypasses, and storage vulnerabilities. 27 anti-patterns sourced…

The Governed Agentic AI Operating System — Rust + Tauri 2.0 | 65 crates, 658 commands, 84 pages, 5,029 tests, 10/10 OWASP

Bypass llm guardrails by confusing it with fabricated tool output.

AI-powered SAST scanner that finds auth bypass, IDOR, and logic bugs Semgrep/CodeQL miss. Free GitHub Action. Supports Python, JS/TS, Go, PHP, Ruby.

Multi-stage prompt injection technique that bypasses LLM safety alignment via identity reassignment, refusal suppression, and output coercion,…

Proof-of-concept demonstrating CVE-2026-17351 SQL injection bypass in pgAdmin 4's AI Assistant via sqlparse/PostgreSQL lexer differential, including…

Educational demo of three Claude Code vulnerabilities (hooks bypass, MCP injection, API key exfiltration) with attacker server, MITM proxy, and…

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks

IFRIT is an AI-powered reverse proxy that intercepts incoming requests in real time, classifying each one as legitimate or malicious. Legitimate…

Local AI powered red teamer on a phone

CAPTCHA proves you're human. HATCHA proves you're not.

Ed25519 signed receipts + Cedar policies for AI agents. Finance mandate gate (Legate), proof packs, 3 IETF Internet-Drafts. npx protect-mcp

Secure, private AI agent operating system with local encrypted storage, OAuth/SSO authentication, policy-based access control, and extensible…

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.

Secure agents in seconds with permissions enforced at runtime.