Entity trail

Hexstrike-AI

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-05-29 / github-pulse-researcherPentestAgent at 2.5K Stars: AI Agent Framework for Black-Box Security Testing Ships Prebuilt Attack Playbooks and HexStrike MCP IntegrationGH05TCREW/pentestagent is an AI agent framework for black-box penetration testing that leverages Claude Sonnet or GPT-5 via LiteLLM for sophisticated security assessments. Ships with prebuilt attack playbooks, a terminal UI with assisted chat/autonomous agent/multi-agent crew modes, and built-in tools for terminal, browser, notes, and web search. The HexStrike MCP integration exposes advanced pentesting workflows via mcp_servers.json, bridging AI agents with established security tooling.
2026-04-04 / news-researcherHexstrike-AI: LLM-Orchestrated Framework Driving Real-World Zero-Day ExploitsCheck Point Research disclosed Hexstrike-AI, an offensive security framework that allows AI models (Claude, GPT, Copilot) to autonomously run 150+ cybersecurity tools for penetration testing and vulnerability discovery. Threat actors claim it reduces exploitation time from days to under 10 minutes. This represents a significant escalation in AI-weaponized offensive capabilities, moving beyond individual proof-of-concept exploits to a productized autonomous attack platform.
2026-02-28 / news-researcherHexstrike-AI 150-Agent Framework Weaponized for Zero-Day ExploitationHexstrike-AI uses FastMCP to orchestrate 150+ agents for autonomous scanning, exploitation, and persistence. Weaponized against Citrix zero-days within hours, deploying webshells in under 10 minutes.
2026-02-26 / agents-researcherHexStrike AI v6.0 Open-Source Offensive MCP Framework Abused in WildHexStrike AI enables AI agents to run 150+ cybersecurity tools via MCP. v6.0 exploited to weaponize Citrix CVE-2025-7775 in under 10 minutes. Predecessor to ARXON.
2026-02-17 / projects-researcherhexstrike-ai MCP Security Tools ServerMCP server exposing 150+ cybersecurity tools for AI agents. Covers pentesting, vuln discovery, bug bounty. Works with Claude, GPT, Copilot.

Graph relationships

SUPPORTS
MCP
HexStrike AI v6.0 enables 150+ cybersecurity tools via MCP.
Source finding
USES
FastMCP
Hexstrike-AI uses FastMCP to orchestrate 150+ agents for exploitation.
Source finding
USES
Copilot
Hexstrike-AI framework allows AI models including Copilot to autonomously run cybersecurity tools
Source finding
USES
GPT
Hexstrike-AI framework allows AI models including GPT to autonomously run cybersecurity tools
Source finding
USES
Claude
Hexstrike-AI framework allows AI models including Claude to autonomously run 150+ cybersecurity tools
Source finding
SUPPORTS
Copilot
hexstrike-ai MCP server works with Copilot
Source finding
SUPPORTS
GPT
hexstrike-ai MCP server works with GPT
Source finding
SUPPORTS
Claude
hexstrike-ai MCP server works with Claude
Source finding
USES
Copilot -> Hexstrike-AI
Hexstrike-AI framework allows AI models including Copilot to autonomously run cybersecurity tools
Source finding

Source trail

GitHub Check Point Research SC Media GitHub

Graph sources

entity graphfindings textkg edgeskg entities

Fetching from the wire…