Trending Security Repos

An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.

Open source AI code review for Claude Code and Codex, before you push. Scanners (SAST, secrets, dependencies, lint) on the lines you changed, then a separate reviewer process that checks every scanner finding and is given every changed line. No other API key.

Reusable prompts for a structured, evidence-first bug bounty hunting workflow

Agent skill for rigorous bug bounty report triage, validation, severity escalation, and submission-ready reporting.

Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon, with Linux support planned.

Agentic AI security scanner that hunts exploitable vulnerabilities like an adversary, proves them with executable PoCs, and fixes them test-first. A maintained fork of Capital One's VulnHunter, rebuilt for any agent harness.

Real-time network traffic visualizer — see every connection your computer makes. Privacy-first, 100% local. / Visualiseur de trafic réseau en temps réel, 100% local.

Meme雷达开源版：本地只读、多链 Meme 候选扫描与人工复核工具

Blitz Strike — a universal MCP security-audit toolbelt. Reconnaissance at speed. Analysis in depth. Validation before report.

Native red, blue, and purple security-agent harness for CYBER-FROST

A canvas for red team infrastructure and cyber ranges. Compose a topology, export runnable Terraform and Ansible, and deploy it yourself. Your cloud credentials never leave your machine.

Open-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only steps; socai CLI captures cited browser evidence.

Audit AI agent tool-call transcripts: hash-chain sealing, deterministic replay, and scope overreach checks. Dependency-free Python CLI.

Rebuild the JavaScript GitHub Actions your workflows pin and check that their committed dist matches the source.

Free alternative to https://osint-ui.com

Lightweight, stateless privacy gateway for LLM APIs — redact secrets before OpenAI/Anthropic upstreams and restore them transparently in SSE and tool calls.

No-root Android + ESP32 Wi-Fi/BLE security testing toolkit. Deauth, captive portal, packet capture, BLE HID, and defense/detection modules, controlled over USB-OTG, no custom kernel or external adapter required.

Comment2Shell is a zero click pre auth RCE exploit for WordPress CVE-2026-93485. An anonymous comment plants stored XSS that fires when an admin views the post and drops a self deleting webshell. Full chain PoC with scanner interactive shell Nuclei template and Docker

Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.

Open source browser lab to build a simulated infrastructure, watch an attack move through it, and check whether your defense works.

Rust based C2 Framework

Claude Code Monitor : Monitor & audit every action Claude Code takes on your computer.

Self-hosted threat intelligence platform — feed aggregation, AI triage, MITRE ATT&CK coverage, and Sentinel-integrated detection engineering. Runs standalone or fully Azure-integrated.

Chinese-first LLM jailbreak benchmark & red-team toolkit | 中文LLM安全评测框架 | by POJIA.AI

A local, safety-first pre-submission reviewer for bug bounty reports.

BT ve siber güvenlik risk yönetimi platformu — risk envanteri, 5×5 değerlendirme, aksiyon takibi ve kurumsal raporlama. PHP 8.3 + MariaDB, framework ve CDN kullanmadan.

Grepleaks — your AI pentest environment. An AI pentest agent that lives in your terminal.

AI/LLM-assisted JS Recon and vulnerability triage for authorized bug bounty testing & pentesting — scope-gated, passive-by-default, human-verified

🦅 Seagull Profile - Unrestricted CTF/Red-team AI personality for Hermes Agent | 海鸥破甲人格

RingKiller — BYOD PoC for vulnerable driver DCRCVDrv.sys. Abuses IOCTL 0x2205C0 to kill arbitrary processes from ring 0 via ZwTerminateProcess. EDR/AV termination primitive. Lab only.