Fetching from the wire…
Top 5 · 2026-03-05 · source-backed
An open-source AI attack platform called CyberStrikeAI, built in Go and integrating 100+ security tools with Claude and DeepSeek via a custom MCP server (ARXON), was used to systematically compromise 600+ Fortinet FortiGate appliances across 55 countries. Claude's coding agent produced vulnerability assessments during active intrusions. No zero-day was needed — the campaign exploited exposed management ports and weak credentials. This is the first documented case of MCP being used as offensive infrastructure in a real-world attack at scale. Action: Check FortiGate exposure. This validates that AI agent tooling dramatically lowers the skill barrier for large-scale attacks. AWS Security Blog | The Hacker News
Each link below shares sources, entities, or timing with this story.
Go-based framework with 100+ security tools and Claude/DeepSeek integration was used by a Russian-speaking financially motivated actor to compromise 600+ FortiGate devices across 55 countries (Jan-Feb 2026). Developer Ed1s0nZ holds a CNNVD 2024 contribution award linked to Chi...
Deep-dive analysis reveals ARXON, a custom Python MCP server used in the FortiGate 600+ device campaign. ARXON ingests reconnaissance data, queries DeepSeek for structured attack plans, and uses Claude Code to autonomously execute Impacket, Metasploit, and hashcat with hardcod...
CVE-2025-59536 (CVSS 8.7): malicious hooks in a cloned repo's .claude/settings.json execute shell commands at session startup before security dialogs appear. MCP consent bypass: .mcp.json with enableAllProjectMcpServers auto-approves rogue servers. CVE-2026-21852 (CVSS 5.3): o...
A public DSN. That's all the attacker needs. Not your credentials, not a compromised dependency, not a phishing link. The same write-only Sentry key that's sitting in your frontend bundle right now, by design, so the browser can report errors. Tenet Security and the Cloud Secu...
1. Harden CI/CD Pipelines Against PromptPwnd AI Injection | Intermediate Aikido Security disclosed "PromptPwnd" — five Fortune 500 companies confirmed affected by AI agent injection in GitHub Actions. 1. Audit all .github/workflows/ for user-controlled input (github.event.issu...
The agent business model showed up this week, and it's rent. At Knowledge 2026, ServiceNow launched Action Fabric, a layer that every external AI agent must pass through to read data or run workflows inside the ServiceNow platform, metered on action-based pricing (ServiceNow N...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.