Introduction: RedAmon has officially surpassed 3,000 GitHub stars, marking a significant milestone for open-source offensive security tooling and agentic AI integration. Version v7.0.1 introduces critical feature upgrades, including a modular plugin platform, Skiller agent session learning, human-reviewed skill versions, and full Model Context Protocol (MCP) native support for automated bug bounty workflows. Learning Objectives & Secrets: Objective 1: Understand how Model Context Protocol (MCP) servers enable external AI agents to securely query and interact with live reconnaissance and attack-surface data.

Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what...

WasmForge compiles GhostPack C# tools to WebAssembly. Surface how Rubeus and Seatbelt run past your AMSI and ETW defenses, signature-free.

samugit83/redamon - Redamon is a cutting-edge, open-source AI-powered agentic red team framework that represents a paradigm shift in the field of automated offensive security. Designed to operate with zero human intervention,... #OpenSource #GitHub

A new open-source offensive security platform called RedAmon is redefining automated penetration testing by chaining reconnaissance, exploitation, post-exploitation, AI-driven triage, and automated c…

A new open-source offensive security platform called RedAmon is redefining automated penetration testing by chaining reconnaissance, exploitation, post-exploitation, AI-driven triage, and automated code remediation all into a single end-to-end pipeline that culminates in a GitHub pull request with the fix already written. RedAmon is a modular, containerized penetration testing framework built on Docker that requires no security tools installed directly on the host system. The platform is architected around six core pillars: a parallelized Reconnaissance Pipeline, an AI Agent Orchestrator, an Attack Surface Graph, EvoGraph for cross-session intelligence, the CypherFix remediation engine, and a 500+ parameter Project Settings Engine. Its complete kill chain is summarized as: Reconnaissance → Exploitation → Post-Exploitation → AI Triage → CodeFix Agent → GitHub PR RedAmon’s recon pipeline launches over 40 industry-standard security tools in parallel, including Subfinder, Amass, Naabu, Masscan, Nuclei, Katana, FFuf, and Arjun inside a Kali Linux container. Each tool’s output feeds directly into a shared Neo4j knowledge graph with 17 node types and 20+ relationship types, giving the AI agent a structured, fully connected, and queryable attack surface in minutes rather than hours. A dedicated AI Gauntlet module extends reconnaissance to AI/LLM surfaces, attacking discovered endpoints with four red-team tools — garak, PyRIT, Giskard, and promptfoo to test for prompt injection, jailbreaks, and data leakage, all mapped to OWASP-LLM and MITRE-ATLAS classifications. At the heart of RedAmon is a LangGraph-based autonomous agent implementing the ReAct (Reasoning + Acting) pattern. The agent progresses through three sequential phases: Informational, Exploitation, and Post-Exploitation, and has access to 14+ security tools via Model Context Protocol (MCP) servers running in a sandboxed Kali environment. These tools include Metasploit for exploit execution, Hydra for credential brute-forcing, Playwright for browser automation, and a full Kali shell with 70+ pre-installed CLI utilities. A Fireteam mode enables the root agent to fan out into multiple specialist sub-agents working in parallel, for example, simultaneously validating credential policies via Hydra, verifying a CVE exploit path through privilege escalation, and mapping XSS vulnerabilities across a frontend. Where most offensive tools stop at discovery, RedAmon goes further with CypherFix, a two-agent automated remediation pipeline. A Triage Agent runs nine hardcoded Cypher queries against the Neo4j graph, correlates hundreds of findings, deduplicates them, and ranks them by exploitability. A CodeFix Agent then clones the target repository, navigates the codebase using 11 code-aware tools, implements targeted fixes in a ReAct loop, and opens a GitHub pull request ready for human review and merge. RedAmon is not fully autonomous by design. A Tool Confirmation system provides per-tool human-in-the-loop gates, pausing agent execution before high-impact operations such as Nmap scans , Metasploit exploits, or Hydra brute-force runs, and presenting inline Allow/Deny prompts in the chat timeline. A Rules of Engagement (RoE) document can be uploaded to auto-configure project-wide constraints, while a Target Guardrail permanently blocks government, military, and educational domains at the framework level. RedAmon was created and is maintained by Samuele Giampieri, an AWS-certified AI Platform Architect with 15+ years of experience in enterprise AI agentic systems, alongside Ritesh Gohil, a Cyber Security Engineer at Workday with 7+ years in penetration testing and 11 published CVEs. The framework supports LLM providers, including OpenAI (GPT-5), Anthropic (Claude Opus 4.6), AWS Bedrock, and Ollama-compatible local models, with more than 400 models dynamically selectable per project. It is available on GitHub . What Features Should AI SOC Have? – Download Free 2026 AI SOC Features Checklist The post RedAmon AI Tool that Chains Reconnaissance, Exploitation, and Post-exploitation appeared first on Cyber Security News .

🤖 REDAMON: ¡El Futuro de los Ciberataques Automatizados con IA! 🎯

A new open-source offensive security platform called RedAmon is redefining automated penetration testing by chaining reconnaissance, exploitation, post-exploitation, AI-driven triage, and automated code remediation all into a single end-to-end pipeline that culminates in a GitHub pull request with the fix already written. RedAmon is a modular, containerized penetration testing framework built on Docker that requires [...] The post RedAmon AI Tool that Chains Reconnaissance, Exploitation, and Post-exploitation appeared first on Cyber Security News .

⭐ 1,618 stars • Python An AI-powered agentic red team framework that automates offensive security operations, from reconnaissance to exploitation to post-exploitation, with zero human intervention.

RedAmon is an open-source AI red team framework that connects reconnaissance, exploit validation, post-exploitation, vulnerability triage, and code remediation in one workflow. The project’s GitHub repository describes it as an agentic security platform that can move from attack surface mapping to a pull request with suggested fixes. The tool runs inside Docker containers, so users […] The post RedAmon AI Tool Chains Reconnaissance, Exploitation, and Automated Remediation appeared first on VPN Central.