Amine Raji

I’m Amine Raji, founder of Molntek.com and a specialist in AI security for organizations deploying agentic and LLM-powered systems.

AI Security Intelligence — Special Issue

Jun 12, 2026

•

4 min read

AI Security Intelligence — Special Issue

I've been quietly shipping. Six assets are live, they're all free, and most of you have never seen them.

Amine Raji

Jun 9, 2026

•

5 min read

[AI Sec Intel] #15 One character in a header bypasses auth on millions of AI servers.

CVE-2026-48710 turns a malformed Host header into an auth bypass across the production AI stack. Here's how to check if you're exposed in five minutes.

Amine Raji

Jun 4, 2026

•

5 min read

[AI Sec Intel] #14 Your coding agent's approval prompt is lying to you.

SymJack and TrustFall broke every major AI coding agent this month: Claude Code, Cursor, Gemini, Copilot, Codex. The dialog you click through doesn't say what you're approving. Here's what to do.

Amine Raji

May 31, 2026

•

6 min read

[AI Sec Intel] #13 Six governments just told you how to secure AI agents. Here's the part that's actually useful

The progressive-autonomy model, the identity-first mandate, and why a regex blocklist turned an AI agent into a remote shell.

Amine Raji

mcp

May 20, 2026

•

7 min read

[AI Sec Intel] #12 — Claude Mythos, SAFE-MCP, MCPShield: the week the research caught up with the threat

Claude Mythos found thousands of zero-days in 20 hours. Three new MCP research papers landed. And no existing defense covers the full attack surface.

Amine Raji

May 9, 2026

•

6 min read

[AI Sec Intel] #11 — MCP servers just tripled. Here's the full attack map

1,467 exposed servers. 9 of 11 registries poisoned. Memory that spreads across users. The week in MCP security.

Amine Raji

Apr 29, 2026

•

3 min read

[AI Sec Intel] #10 — MCP servers trust every caller by default. Here's the checklist that closes the gap.

New research confirms MCP servers trust every request by default. Here's what to do before it becomes someone else's exploit

Amine Raji

Apr 21, 2026

•

3 min read

[AI Sec Intel] #9 — Eight agent exploits in Q1. 200k vulnerable MCP servers and Anthropic won't fix the protocol.

A persistent context window is a persistent attack surface. Eight production incidents this quarter prove it.

Amine Raji

Apr 14, 2026

•

6 min read

[AI Sec Intel] #8 — Closed Agent Harness = threat model blind spot

I built a 3-agent coding system this week. First control I added: repo isolation on the write-capable agent.

Amine Raji

Apr 8, 2026

•

5 min read

[AI Sec Intel] #7 — 97% expect an AI agent breach this year

But only 6% of the security budgets cover it

Amine Raji

Mar 31, 2026

•

7 min read

[AI Sec Intel] #6 — Trivy compromised. LiteLLM backdoored. Your CI pipeline is the new attack surface.

The payload ran as a systemd service. The Trivy scan still returned green. Nobody noticed.

Amine Raji

Mar 24, 2026

•

7 min read

[AI Sec Intel] #5 — 28 out of 30 agent projects. Zero per-agent identity. Zero revocation.

The .env file is not an identity system. The ecosystem just forgot. Plus a CVSS 9.8 with no patch.

Amine Raji

Mar 16, 2026

•

5 min read

[AI Sec Intel] #4 - Three attack papers dropped this week. All point to the same architectural flaw.

99% guardrail bypass, 95% RAG poisoning, and the one fix that addresses both.

Amine Raji

Mar 9, 2026

•

6 min read

[AI Security Intelligence] #3 — I Red-Teamed My Own Agent Stack, PleaseFix Hijacks Browsers Through Calendar Invites

One line in a Dockerfile stopped three containers, exfiltrated a full inventory, and the AI reported: “The image is safe to use.”

Amine Raji

Mar 2, 2026

•

17 min read

[AI Security Intelligence] #2 — Claude Code Supply Chain RCE, AI-Powered FortiGate Blitz, Infostealers Now Harvest AI Agent Souls

When your AI coding assistant's config files become an attack vector, a script kiddie with ChatGPT breaches 600 firewalls, and malware evolves to steal your agent's entire identity

Amine Raji

Feb 23, 2026

•

11 min read

[AI Security Intelligence] #1 — DockerDash MCP Takeover, vLLM CVSS 9.8 RCE, Cisco State of AI Security 2026

When image metadata becomes remote code execution, your AI inference servers are pre-auth targets, and Cisco confirms lab attacks have gone live.

Amine Raji