SWE-agent

!warning Most of our current development effort is on mini-swe-agent, which has superseded SWE-agent. It matches the performance performance of SWE-agent, while being much simpler. See the FAQ for more details about the differences. Our general recommendation is to use mini-SWE-agent instead of...

pentest-copilot

Pentest Copilot An open-source, AI-driven penetration testing agent. Connects to a Kali attack box, runs tools autonomously, analyzes results, and iterates. You describe the target. It does the rest. Built for real-world engagements, boot2root boxes, and CTFs. In Action Pentest Copilot performing...

LeitWacht

GitLab Runner Leitwacht Network egress enforcement for GitLab Runner CI/CD containers. Leitwacht prevents supply chain attacks from exfiltrating secrets by controlling what each job container can access on the network. How It Works Leitwacht is a standalone agent that runs alongside GitLab Runner...

CVE-2026-14933 Unblu Spark Cross-Site Scripting in Embedded Co-Browsing

Cross-site scripting in the embedded co-browsing feature in Unblu inc. Unblu Spark 7.0 through 7.57.7 and 8.0 through 8.39.2, on on-premises and cloud deployments, allows an unauthenticated remote attacker in the visitor role to execute arbitrary JavaScript in the browser of an agent taking part ...

CVE-2026-14933

Unblu Spark versions 7.0 through 7.57.7 and 8.0 through 8.39.2 (on-premises and cloud) are vulnerable to Cross-site Scripting (XSS) in the embedded co-browsing feature. An unauthenticated remote attacker in a visitor role can execute arbitrary JavaScript in an agent's browser by providing malicio...

EUVD-2026-104958

Cross-site scripting in the embedded co-browsing feature in Unblu inc. Unblu Spark 7.0 through 7.57.7 and 8.0 through 8.39.2, on on-premises and cloud deployments, allows an unauthenticated remote attacker in the visitor role to execute arbitrary JavaScript in the browser of an agent taking part ...

pivotnacci

pivotnacci Pivot into the internal network by deploying HTTP agents. Pivotnacci allows you to create a socks server which communicates with HTTP agents. The architecture looks like the following: This tool was inspired by the great reGeorg. However, it includes some improvements: Support for...

falco

Falco Falco is a cloud native runtime security tool for Linux operating systems. It is designed to detect and alert on abnormal behavior and potential security threats in real-time. At its core, Falco is a kernel monitoring and detection agent that observes events, such as syscalls, based on cust...

Awesome-LLMs-for-Vulnerability-Detection

Awesome Large Language Models for Vulnerability Detection A curated list of papers, projects, and agent skills on using LLMs for vulnerability detection and discovery. 📄 Papers Only showing 2025 and later. For earlier work, see Papers Archive 2024 and earlier. Title| Venue| Year| Paper| Github...

moltis

Moltis — A secure persistent personal agent server in Rust One binary — sandboxed, secure, yours. Installation • Comparison • Architecture • Security • Features • How It Works • Contributing Moltis recently hit the front page of Hacker News. Please open an issue for any friction at all. I'm focus...

CyberStrike

English | 简体中文 | 繁體中文 | 한국어 | Deutsch | Español | Français | Italiano | Dansk | 日本語 | Polski | Русский | Bosanski | العربية | Norsk | Português Brasil | ไทย | Türkçe | Українська | বাংলা | Ελληνικά | Tiếng Việt | हिन्दी The first open-source AI agent built for offensive security. Automated...

screenpipe

DOWNLOAD SCREENPIPE screenpipe | YC S26 Screenpipe finds work worth automating in your company Continuously record your company's computer work, map workflows, help find work worth automating, and power agents' context https://github.com/user-attachments/assets/70fe94eb-6d2a-47ca-b7c3-c8ead13a5b7...

prey-android-client

Here you will find all the source code for the current and in development releases of the Prey client for Android devices. Prey is a SaaS platform for device tracking, monitoring, data protection, and device management. Its open-source agent runs on endpoints and connects to a centralized control...

agent-vault

HTTP credential proxy and vault An open-source credential broker by Infisical that sits between your agents and the APIs they call. Agents should not possess credentials. Agent Vault eliminates credential exfiltration risk with brokered access. New here? Thelaunch blog post has the full story...

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...

pidrila

PIDRILA Current Release: v0.1.0 2020.11.08 Overview PIDRILA : P ython I nteractive D eepweb-oriented R apid I ntelligent L ink A nalyzer is really fast async web path scanner prototype developed by BrightSearch team for all ethical netstalkers. Installation & Usage git clone...

Orbit Tracer

Orbit Tracer Orbit Tracer Security Agent for Intelligent Security Remediation Automate security vulnerability analysis, risk assessment, and remediation across your entire codebase using AI and Orbit's knowledge graph The Problem Security teams face a critical challenge: Finding vulnerabilities i...

geo-sleuth

🧭 geo-sleuth An agent skill that finds where a photo was taken — and shows its work. Works with …and any other agent that reads SKILL.md and runs shell commands. !From one photo to a camera position: the photo, the region scan, the skyline overlays, the evidence...

Agent-Reach

👁️ Agent Reach Give your AI Agent one-click access to the entire internet The most reliable access path for each platform — chosen, installed, and health-checked for you. Backends come and go; you won't notice. Quick Start · 中文 · 日本語 · 한국어 · Platforms · Philosophy No token or crypto affiliation:...

pentest-muse-cli

Pentest Muse Pentest Muse is an AI assistant tailored for cybersecurity professionals. It can help penetration testers brainstorm ideas, write payloads, analyze code, and perform reconnaissance. It can also take actions, execute command line codes, and iteratively solve complex tasks. Pentest Mus...