Blog

The latest about AI’s
security blind spots

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Featured

Agentic Security Is Stuck in a Semantic Maze - And We Can't Escape Until We Map It

Agentic AI is GenAI with limbs. Your favorite LLM can now stand up, grab tools, and walk into your stack.

When AI Agents Browse Unprotected: A Security Audit of OpenClaw × Moltbook
February 19, 2026
15 minutes

*A technical security analysis of the OpenClaw ↔ Moltbook integration, February 2026*

Matan Levi, PhD
Security
Designing safe production AI agents via tool scoping: the outreach agent use-case
February 19, 2026
10 minutes

It’s tempting to build an “agent” by handing it every tool it might need: a browser, a search API, an email client, and maybe even direct database access.

Nitsan Bar, PhD
Security
Agentic Security Is Stuck in a Semantic Maze - And We Can't Escape Until We Map It
February 6, 2026
6 minutes

Agentic AI is GenAI with limbs. Your favorite LLM can now stand up, grab tools, and walk into your stack.

Michael Brown
Security