
ironcurtain
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

A security scanner for your LLM agentic workflows

Fully automatic censorship removal for language models


PoC code from DEF CON 25 presentation

AI-powered offensive security testing using autonomous agents, directly in your terminal.

AI-powered vulnerability scanner extension for Burp Suite with multi-provider support (Ollama, OpenAI, Claude, Gemini)

Security tool to find potential vulnerable Server Side Request Forgery (SSRF) parameters.

Repository for CoSAI Workstream 4, Secure Design Patterns for Agentic Systems

DECeption with Evaluative Integrated Validation Engine (DECEIVE): Let an LLM do all the hard honeypot work!

Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks

eBPF-powered Linux observability with AI incident detection. AGPL-3.0 licensed.

Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.

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

A minimal LLM-powered zero-day vulnerability scanner by AISLE.

Secure agents in seconds with permissions enforced at runtime.

A native policy enforcement layer for AI coding agents. Built on OPA/Rego.

WASM sandbox with capability enforcement for AI agent code. Agents can only call explicitly provided tools with defined constraints. Sandboxed…