Open-source Kiro CLI agent fleet for fixed-model multi-agent orchestration across coding, design, security, vision, planning, and VAPT.
-
Updated
Sep 9, 2026 - HTML
Open-source Kiro CLI agent fleet for fixed-model multi-agent orchestration across coding, design, security, vision, planning, and VAPT.
🎯 Automated AI Safety Red Team Agent for systematic model safety probing, policy boundary verification, and regression tracking.
A Dify plugin that integrates Nmap for powerful network scanning, mapping, and security auditing directly within Dify workflows.
Local security agent for the Hermes host. Flask portal on 127.0.0.1:9193, dry-run mode. Daily 6 PM PT cron security report.
An autonomous reflective Go agent for full-cycle security auditing, WAF evasion, OOB LDAP verification, self-remediation (auto-patching), and compliance reporting for CVE-2021-44228 (Log4Shell).
Comprehensive cybersecurity agent benchmark suite with isolated public tasks, evaluator materials, provenance and reproducible release checks
SecMonLite (GhostSec)
Security reconnaissance preset for DeepSeek Harness with evidence backed reporting.
An enterprise Claude security agent for GitHub, packaged as reusable org-level workflows. Drop a few lines into any repo in your org and every pull request and push is automatically reviewed for OWASP Top-10 issues, scanned with GitHub Advanced Security (CodeQL, Dependabot, secret push protection), gated by severity, and — for critical/high finding
Autonomous SUSE MLM Security & Compliance Agent with LangGraph, FastMCP, FastAPI, React, and PostgreSQL
Dataset for Training and Evaluating LLM-Based SOC Agents
使用 CloudFormation 一键部署 OWASP Juice Shop 测试环境(CloudFront + ALB + ECS Fargate),用于 AWS Security Agent 渗透测试实验
Diff-aware security scanner for GitHub PRs — flags mutable Express/NestJS/Next.js routes with no auth middleware and responses leaking sensitive fields. Deterministic, AST-based, human-in-the-loop.
Local-first threat detection agent for Windows. Runs a 4B-parameter LLM (Qwen3.5-4B) on-device via KoboldCpp. ReAct FSM, MITRE ATT&CK, YARA, OSINT, 15 skills, 4000+ tests.
Controlled security validation agent that reproduces reconnaissance findings and records evidence.
Zero-dependency PowerShell agent for Windows endpoint posture: IIS discovery, 15 hardening checks, software inventory, heartbeat. MIT.
One light open-source security agent (eBPF/ETW) feeding a canonical, fix-first Findings Engine. OCSF-native, no per-seat license — you own your data.
Security Agent Demo
An open-source AppSec agent that reasons like an analyst: real scanners, your org's context, and a conversation instead of 400 findings.
To associate your repository with the security-agent topic, visit your repo's landing page and select "manage topics."