
TraceTree
Runtime behavioral analysis tool that sandboxes suspicious packages in Docker, traces syscalls with strace, maps process cascades into directed…

Runtime behavioral analysis tool that sandboxes suspicious packages in Docker, traces syscalls with strace, maps process cascades into directed…

Stalk your Friends. Find their Instagram, FB and Twitter Profiles using Image Recognition and Reverse Image Search.

SAFE embeddings to match functions in yara

Serverless AWS security automation framework that ingests threat intelligence, applies ML-based anomaly detection (RCF, IP Insights), and enriches…

Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

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

Collects multi-source security logs from reproducible Docker attack scenarios, builds attack chains, and provides the SecLog-Bench-216 benchmark for…

Runtime guard skill that detects and blocks malicious skill-induced attacks in skill-augmented agents, with an MCTS loop that evolves the guard…

Multi-agent automated context management for long horizon tasks in local AI Agents

Suppress vulnerabilities applying Kubernetes context to scans

FARO - Document Sensitivity Detector

The world's fastest agentic crawler. Reclaimed. Reinvented. Ready for war.

Fix-Like Artifacts With Embedded Defects

A benchmark for evaluating AI agents on fixing real-world security vulnerabilities.

Restructured and Collaborated SIEM and CVSS Infrastructure. Presented at Blackhat Asia Arsenal 2020.

VulnAgent-X: A Layered Agentic Framework for Repository-Level Vulnerability Detection

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞