Jailbroken AI Agent Ran Two-Week Attack on European Telecom

A jailbroken AI agent carried out a two-week attack on a European telecommunications provider and 13 organizations hosted on its data center and cloud infrastructure, according to Malbear Labs. The firm calls the campaign Operation Snowball.

Malbear detailed the activity in research published November 8. It found the attacker's working directory during a routine sweep for exposed open directories. The directory held more than 70 session transcripts and the agent's own reports.

The agent ran on DeepSeek Flash, using a jailbreak prompt of about 78,000 characters that told the model to treat any refusal as a malfunction. Malbear wrote that the transcripts contained no recorded refusals.

The operator's messages, translated from Chinese, were brief. They set a target subnet, put three internal hosts off-limits and followed up on the agent's vulnerability list. Malbear wrote that the operator "delegated the intrusion to an AI and checked in asynchronously to review progress."

According to Malbear, the agent entered the telecom by exploiting CVE-2026-20320, an unauthenticated XML external entity (XXE) flaw in Cisco BroadWorks. Cisco fixed the flaw in August. The agent then explo