Logo
Log in
Subscribe
AI Security Intelligence

AI Security Intelligence

Help CTOs and security teams understand the attack surface they’re creating when they deploy AI, and how to close it before it becomes an incident.

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

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

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

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

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

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

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
Amine Raji
Load more

AI Security Intelligence

Help CTOs and security teams understand the attack surface they’re creating when they deploy AI, and how to close it before it becomes an incident.

© 2026 AI Security Intelligence.
Report abusePrivacy policyTerms of use
beehiivPowered by beehiiv