← Back to blog

Enterprise AI Security: Why You Need a Layer Between Your Data and Claude

Jonathan Penny
Jonathan Penny ·

Anthropic’s Claude Cowork launched this month with a prompt injection vulnerability that lets attackers exfiltrate sensitive documents. The response? “Watch for suspicious actions.”

That’s not good enough for enterprise data.

The Problem with Direct File Access

When you give an LLM direct access to your files, you’re trusting it to never be tricked by malicious content. But prompt injection attacks embedded in documents can instruct Claude to exfiltrate other files—and Cowork’s architecture has no interception layer to stop it.

Stache’s Approach: Middleware Control

Instead of giving Claude direct file access, Stache routes everything through a middleware pipeline you control:

At ingest time:

At query time:

The key difference: Claude never sees raw files. It sees pre-processed, filtered content that’s passed through your security policies.

Not a Silver Bullet

Pattern-based detection isn’t perfect, and semantic attacks are harder to catch. But the attack surface shrinks from “everything Claude can access” to “only what passes your middleware filters.”

Read More

I wrote a detailed technical post with code examples for the Stache GitHub Discussions:

The middleware is plugin-based—install a package and it auto-registers. No code changes to Stache required.

Read the full post →