Vector embeddings have been a blind spot for privacy and security teams. VectorLens scans them to uncover unsecured sensitive data. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏

View in browser

Greetings,

I'm excited to announce the launch of VectorLens, a free-to-try command-line tool that runs locally in your own infrastructure to privately scan your vector embeddings and generate a report letting you know if it found any PII or other sensitive data and how prevalent it is.

AI is pretty much the worst thing to ever happen to data privacy and security. It's amazing stuff, but data is flying everywhere and getting duplicated like crazy.

One place it gets copied to is vector embeddings, which are typically stored in vector databases as a thematic content index used by AI and agents.

The trouble for the past couple of years has been that people don't know if their embeddings are a problem. That's because there haven't been any tools that look at them and tell you what risks lurk within. Until now.

VectorLens is a way for folks in privacy and security to make the case for why it's a problem and what to do about it. If you're interested in shining a light on the dark data in AI, please check out VectorLens or read the just-dropped blog with the story of how it came to be.

..Patrick

Patrick Walsh
CEO, IronCore

Announcing VectorLens: See the PII Hiding in Your Vector Embeddings

A Flashlight for the Darkest Corner of Your AI Stack

AI quietly copies your sensitive data into vector embeddings that no PII scanner can read. VectorLens is a new local CLI tool that scans embeddings to find PII hiding in your AI pipelines.

> Read the full blog

The AI Vulnerability Tidal Wave

Security Strategies Need to Adapt or Drown

Vulnerabilities are up, exploits are happening ahead of patches, and AI is fueling all of it. See the data showing the new reality for security teams and what it means for the future of breaches.

> Read the blog

OWASP SnowFROC '26:
Hacking AI-Enabled Apps

Exploit Demos, Data Compromises, and Hardening Patterns

This is a talk that IronCore CEO Patrick Walsh delivered first at the SnowFROC conference. It contains exploit demos, data compromises, and hardening patterns for AI-integrated applications. There's a focus on recent agentic systems like OpenClaw and some suprprisingly optimistic results as Patrick shows just how far AI security has come in the last few months. But also how far it still has to go.