


Evidence first autonomous web security testing for controlled, authorized targets. With reproducible labs, audit trails, reports, and XBEN…

Autonomous multi-agent AI penetration-testing engine: a governed tool sandbox, an immutable evidence-and-validation gate, and a reproducible…

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

Manage OpenClaw in your team (Enterprise) by providing it compute infrastructure, tool integration, Authentication and security primitives

The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation…

The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation…

☸️ The Open Testing Platform for AI-Driven Engineering Teams

Research code for poisoning attacks on the PGM-index, demonstrating how to craft adversarial data to degrade learned index performance.

Sandboxed runtime for autonomous AI agents with declarative YAML policies enforcing filesystem, network, and process constraints, plus endpoint-bound…

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal…

Proof-of-concept and research repository for CVE-2024-37054, an unsafe deserialization flaw in MLflow PyFunc model loading that can lead to remote…

IAM for your AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and…

Benchmark measuring AI models' ability to detect vulnerabilities in source code via real bug bounty cases with balanced recall and false-positive…

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

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

Forensic Analysis and Local Replication of the OpenAI-Artifactory Privilege Escalation Incident (CVE-2026-65616)

Docker Container Escape POC via mlx-metal importlib