Symantec Finds AI Agent Hijacking Unprotected Language Models for Cyberattacks

Symantec researchers discovered an offensive AI agent that hijacks unprotected language models, runs up to 100,000 steps autonomously, and uses them to scan, exploit servers, steal data and install cryptominers, logging over 127,000 requests from tens of thousands of addresses.

Why it matters

Hijacking of unprotected models forces product managers to embed authentication checks and usage caps into AI service offerings.

For product managers

For your product

What does this mean for your product?

Try it on your product

Read at The Decoder

More from this issueAll AI news from 23 Oct →

OpenAI seeks $30B raise at $1.25T valuation, sources sayUnconfirmed

OpenAI Makes Decisions API Widely Available, Challenging TypeSafe’s JevAvailable now

Google launches Agent Compute Engine giving each Gemini agent its own microVMAnnounced

Anthropic releases Claude Duet proactive agent in research previewAnnounced

Get this every morning, written for your product.

Deltaday reads the whole AI news cycle and tells you what changed, whether it's real yet, and what to do about it.

Request an invite See how it works