
security-harness
Multi-agent static application-security review harness for AI coding agents: maps codebases, hunts vulnerability classes, chains and verifies…

Multi-agent static application-security review harness for AI coding agents: maps codebases, hunts vulnerability classes, chains and verifies…

Sandbox for AI coding agents. Runs Copilot CLI, Claude Code, OpenCode, Gemini CLI, Antigravity, Pi, goose or a plain shell inside a kernel-level…

Top-level repository for LFI: Practical, Efficient, and Secure Software-based Sandboxing

Service that builds enrolled open-source repositories in isolated offline VMs and scans them for security vulnerabilities, emailing findings with…

Example AI-agent taskflows and MCP servers for auditing source code, triaging issues, and detecting vulnerabilities across web, Android, and iOS…

Rootless container runtime and sandbox that launches kernel-enforced OCI images in milliseconds with no daemon, featuring resource profiles, seccomp…

🔎 Static code analysis engine to find security issues in code.

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

Reachability triage for vulnerability scans. Feeds scanner findings to an LLM agent that reads your source and decides which CVEs are actually…

A secure low code deception runtime framework, leveraging AI for System Virtualization.

Let your AI go full send. Your home directory stays home.

Proof-of-concept demonstrating a Node.js permission model bypass (CVE-2026-21636) that allows network access via undici/fetch to local services,…

Rusty Hypervisor - Windows Kernel Blue Pill Type-2 Hypervisor in Rust (Codename: Matrix)

Security scanner auditing Claude Code environments for CVE-2026-21852 pre-trust execution, hook hijacking, and eBPF lockdown.

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


Deliberately vulnerable Java/Maven fixture for testing Log4Shell (CVE-2021-44228) detection, code-impact classification, and remediation guidance in…

LLVM-based security research toolchain: NeverC, a C23 cross-compiler, and NeverD, a binary analysis and decompilation engine that lifts PE, ELF,…