
secprbench
Benchmark of 265 real vulnerability-introducing code changes across nine C, C++, and Rust projects, with paired review tasks, Docker sandbox, judge,…

Benchmark of 265 real vulnerability-introducing code changes across nine C, C++, and Rust projects, with paired review tasks, Docker sandbox, judge,…

Reverse-engineering workbench built on Ghidra's decompiler with a native Java-free engine, AI-assisted function analysis, byte patching, sandboxed…

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

Executes untrusted Python, JavaScript, and Bash in a hardened jail with 5-second, 128 MB, 0.5-core, PID and output limits.

dex-vm used to protect the android classes.dex file

End-to-end security audit framework for LLM agents: static AST and taint modeling, attack synthesis, Docker sandbox replay, and deterministic verdict…

a fully autonomous AI agent for reverse engineering

A search-first, profile-aware reverse-engineering workspace for AI agents — 735 tools across 36 domains in one MCP server.

Offline SAST/DAST triage engine that parses source code and replays HAR traffic to detect business-logic flaws, BOLA, race conditions, and privilege…

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

Reverse engineer anything with agents, from app behavior down to native binaries.

Windows artifact analysis toolkit that maps AV detections to PE offsets, sections, RVA/VA and strings, with YARA, AMSI, capa and multi-engine…

A Windows runtime analysis toolkit combining memory scanning, debugging, automation, and AI-friendly APIs.

Windows kernel-level debugger with OllyDbg/IDA-style UI, software and hardware breakpoints, PDB symbols, decompiler, and 17 plugins for reverse…

Go CLI that deobfuscates javascript-obfuscator (obfuscator.io) output and unminifies JavaScript using AST transforms, static decoding, and a goja…

Config-driven Dart AOT snapshot analyzer that exports blutter-compatible symbols and structs for IDA, radare2 and Frida, and decompiles functions…

Reference implementation for "Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution". Out-of-band Epistemic Andon Cord,…

Evidence-oriented DAST scanner in Go that crawls web apps and APIs, then runs adaptive SQLi, XSS, RCE, SSRF, and auth checks with replayable proof.