defending-code-reference-harness

Defending Code Reference Harness A reference implementation for autonomous vulnerability discovery and remediation with Claude, based on our learnings from partnering with security teams at several organizations since launching Claude Mythos Preview. For a write up of these learnings along with...

autonomous-offensive-llm-handbook

📖 Read the handbook online : follow the lessons from your first fixture run to an agent with clear limits. The model proposes, the code disposes AUTONOMOUS SECURITY / THE BUILDER'S FIELD MANUAL Read the website · Start the course · Run the lab · Connect your model · The build sequence A practical...

CVE-2021-21978

CVE-2021-21978 CVE-2021-21978 RCE exp Affected versions VMware View Planner Harness 4.X Similar to CVE-2021-21978, this vulnerability allows uploading arbitrary files without authentication, and achieving remote code execution by modifying the built-in py script. It is worth noting that commands...

FFM

Freedom Fighting Mode FFM FFM is a hacking harness that you can use during the post-exploitation phase of a red-teaming engagement. The idea of the tool was derived from a 2007 conference from @thegrugq. It was presented at SSTIC 2018 video and the accompanying slide deck is available at this url...

evmbench-certora-agent-harness

EVMBench Certora Agent Harness Configurable agent harness for iterative smart-contract spec generation/refinement using: EVMBench-style tasks openai/frontier-evals - project/evmbench Certora Prover Certora/CertoraProver LLM backend: OpenAI API, OpenRouter API, local Ollama, or mock mode What this...

drinkme

drinkme drinkme is a shellcode test harness. It reads shellcode from stdin and executes it. This allows pentesters to quickly test their payloads before deployment. Formats drinkme can handle shellcode in the following formats: "0x" "\x" "x" "" For example, NOP could be represented as any of...

fuzzable

Fuzzable Framework for Automating Fuzzable Target Discovery with Static Analysis Introduction Vulnerability researchers conducting security assessments on software will often harness the capabilities of coverage-guided fuzzing through powerful tools like AFL++ and libFuzzer. This is important as ...

SetCookieAnalysisInBrowsers

Set Cookie Analysis in Browsers License Released under AGPL see LICENSE for more information. Description For more information see the following blog post: https://www.nccgroup.com/en/blog/2015/01/analysis-of-setting-cookies-for-third-party-websites-in-different-browsers/ Usage The "victimsite"...

codeql

CodeQL This open source repository contains the standard CodeQL libraries and queries that power GitHub Advanced Security and the other application security products that GitHub makes available to its customers worldwide. How do I learn CodeQL and run queries? There is extensive documentation abo...

LangAlpha

The harness for agentic trading. Open-source AI agents that research the market, build the thesis, and trade your own brokerage account within the permissions you set. Try LangAlpha ↗ · Get started · Agentic trading · Harness design · Full-stack architecture · Security English · 简体中文 · 日本語 Why...

CVE-2026-1312-Testing

CVE-2026-1312 Reproduction Clone the Repository Setup Requirements: Python 3.12 installed Docker Desktop installed and running Run the Script ./runcve20261312.sh Files runcve20261312.sh Main execution script docker-compose.yml Docker configuration .dockerfile Docker image setup requirements.txt...

autoharness

AutoHarness Created by Akshat Parikh What is this tool? AutoHarness is a tool that automatically generates fuzzing harnesses for you. This idea stems from a concurrent problem in fuzzing codebases today: large codebases have thousands of functions and pieces of code that can be embedded fairly de...

Agent-Security-Regression-Harness

OWASP Agent Security Regression Harness The OWASP Agent Security Regression Harness is an open source, vendor-neutral test harness for running executable security regression scenarios against agentic applications and MCP-integrated systems. The project helps builders and defenders verify that...

toothpicker

ToothPicker ToothPicker is an in-process, coverage-guided fuzzer for iOS. It was developed to specifically targets iOS's Bluetooth daemon bluetoothd and to analyze various Bluetooth protocols on iOS. As it is built using FRIDA, it can be adapted to target any platform that runs FRIDA. This...

Shellcode-Test-Harness

Shellcode Test Harness A lightweight test harness designed to speed up shellcode development by providing an execution environment with integrated crash diagnostics and debug output redirection. Features Executes shellcode via module stomping Uses VEH to catch crashes: If the shellcode faults, it...

deleting-the-trace

Control-token injection attacks on tool-using agents Code and logged measurements for a study of two input-level attacks on tool-using language model agents. The first attack appends a short string of a model's own channel-control tokens to untrusted input; the tokenizer reads it as an...

linux-kernel-codex-harness-v2

Kernel Codex Harness v2 한국어 | English Research Tool · Original Import: 3 April 2026 · v2 Documentation Revision: 11 July 2026 External Signal: From Attention Allocation to Provenance-Aware Triage Use reproducible observations to guide model attention, then use repository provenance to organize...

security-harness

Security Harness A multi-agent application-security review harness for Claude Code and, later, other AI agents. One router skill dispatches to a full offensive-security pipeline that maps a codebase, hunts vulnerabilities with a per-class knowledge base, chains findings into escalations, verifies...

security-research

security-research Proof-of-concept code and technical write-ups for vulnerabilities I discovered and reported through coordinated disclosure. Every entry here is already public: the vendor advisory is published and a fixed release is available. Nothing under embargo or in draft is included. The...

pentest-harness

Pentest Harness Heaven for Hackers — the professional security testing workspace. An open-source, dark-first AI agent harness for authorized penetration tests, bug bounty research, security labs, and CTF engagements. Built on a plugin architecture where every layer — model adapters, tools,...