
RevShell
A comprehensive educational repository demonstrating the evolution of a Windows reverse shell implant, from a simple proof‑of‑concept (v1.0) to a…

A comprehensive educational repository demonstrating the evolution of a Windows reverse shell implant, from a simple proof‑of‑concept (v1.0) to a…

Merlin is a cross-platform post-exploitation HTTP/2 Command & Control server and agent written in golang.

Forensic toolkit and agent skills for investigating Rails Active Storage/libvips CVE-2026-66066: detects crafted blob indicators, exposure windows,…

Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated payloads, data exfiltration, and…

SOCKS5 proxy tunneled through Cloudflare R2 object storage, with Python and dependency-free C++ agents relaying TCP traffic via encrypted R2 objects…

BlockGuard is a Windows Data Loss Prevention (DLP) agent that intercepts and controls file access at the process level. It ensures that only…

Sensitive info disclosure via info API in PictShare < 3.7.1 (CWE-522). PoC + advisory writeup.

Find and redact secrets in AI coding agent histories (Claude Code, and more).

Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

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

Automated OSINT framework for reconnaissance, data harvesting, and threat intelligence gathering with modular crawlers, scanners, and extraction…

Open-source AI agent firewall that scans HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, emitting verifiable…

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection…

Security control plane for LLM agents: allowlists, owner kill switch, PIN sessions, rate limits, prompt-injection detection, and output scrubbing to…

Full static & memory analysis of Overlord RAT: Go agent architecture, HTTP/2 + WebSocket C2, reflective DLL injection, browser keylogging, and IOCs.…

Security benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…

"Reverse engineering analysis of Agent Tesla, a .NET-based info-stealer that uses APC injection, token manipulation, and registry persistence.…

Monitor large transactions on Polymarket and Kalshi prediction markets with anomaly detection