
seclab-taskflows-fuzzing
An LLM-driven fuzzing pipeline powered by the GitHub Security Lab Taskflow Agent

An LLM-driven fuzzing pipeline powered by the GitHub Security Lab Taskflow Agent

Black-box input-stage purification defense that neutralizes backdoor attacks on object detectors via corruption, diffusion reconstruction, and DBSCAN…

Agentic reverse engineering IDE with a pure-Rust multi-architecture disassembler, native decompiler, debugger, and LLM agent for binary analysis and…

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

Open-source, 100% reproducible AI Agent Runtime Security Benchmark & Sandbox Environment (RFC-010 Draft Protocol).

Natural-language Android automation agent that drives real devices via ADB, captures Logcat and screenshots, and exposes an MCP server for AI IDEs…

Fix-Like Artifacts With Embedded Defects

Capability-based WASM runtime for executing untrusted AI-generated code with enforced CPU, memory, time, I/O, and filesystem limits. Provides…

Evidence-focused malware reverse engineering with deep PE/.NET inspection, Ghidra reconstruction, AI cross-checks, YARA, and ELF debugging

A benchmark for LLM-driven bug discovery: 77 challenges across 43 open-source projects (C/C++/Java).

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

FastGPT Python sandbox escape chain audit tool (CVE-2026-32128 related, v4.14.8 inspect chain)

Benchmarking framework for evaluating computer-use AI agents against multi-step indirect prompt injection, with automatic adversarial goal…

Dylib injection for iOS 11.0 - 11.1.2 with LiberiOS and Electra jailbreaks

Traces user inputs to detect injection vulnerabilities in Java methods via JDWP and Frida, identifying potential command and SQL injection points.


OpenAnt from Knostic is the leading open source LLM-based vulnerability discovery product, helping defenders proactively find verified security flaws…

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