
penthera
Offline cyber security agent for your apps and AI coding tools. Open R&D: measured in public, improved every release.

Offline cyber security agent for your apps and AI coding tools. Open R&D: measured in public, improved every release.

Hardens binaries, Electron ASAR, JS, WASM, Python, and model files against AI reverse-engineering agents using decoy metadata, budget exhaustion, and…

nas: a zero-dependency Python CLI + MCP server for Synology DSM 7. One-command audit and fix for the C3RB3R / .L0CK3D ransomware campaign; hand it to…

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

OpenAI compaction research: GhostCompact + Compaction Smuggling

Replication package studying how LLM vulnerability auditors defer to static-analysis evidence, with a tree-sitter C/C++ front end, controlled…

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

Sentinel — DeanWay Labs' inbound governor. Guards what an AI agent hears: world content is data, never orders. The mirror of QuietOS.

Agentic harness that automates vulnerability discovery and validation, orchestrating AI-driven analysis workflows to confirm exploitable findings.

Creates CycloneDX Bill of Materials (BOM) for your projects from source and container images. Supports many languages and package managers. Integrate…

Claude Code and Codex skill for finding potentially vulnerable Brotli copies and guiding updates for CVE-2026-111497.

Cross-agent tracing and security-diagnosis system for tool-using LLM agents: normalizes trace events, builds provenance graphs, extracts…

Reachability triage for vulnerability scans. Feeds scanner findings to an LLM agent that reads your source and decides which CVEs are actually…

YARA-inspired prompt pattern matching engine that combines keyword, regex, semantic similarity, and LLM evaluation rules to detect jailbreaks and…

GitLab Duo DevSecOps loop where a second AI re-attacks every AI-written fix, saving each successful bypass as a permanent antibody replayed in CI and…

Find code that runs without you asking: repo files that execute on folder open (VS Code tasks, agent hooks, MCP, devcontainers) and Python…

decomp.wtf fork: Windows PE matching, MinGW/clang-cl toolchains, and an optional REA MCP bridge

[🎖️ Honorable Mention in HAIPS @COLM'26] The first benchmark to evaluate how well do LLM agents act in alignment with their assigned authorization…