# Operation Snowball: a jailbroken DeepSeek agent ran a two-week telecom intrusion

> Source: <https://malbearlabs.com/posts/operation-snowball-inside-an-autonomous-ai-intrusion-campaign>
> Published: 2026-11-08 00:00:00+00:00

**Recommendation:** Treat LLM-driven intrusion harnesses as a live threat: patch unauthenticated XXE like CVE-2026-20320, remove default database credentials, and assume blocked tooling will be replaced by agent-written alternatives such as Perl tunnels.
More in the playbook "Securing agents and AI tools": <https://wpnews.pro/playbooks/agent-security>

Malbear Labs found an open directory holding the live workspace of an autonomous intrusion harness: more than 70 session transcripts, tool staging, credential caches and exfiltrated data from a campaign against a European telecom provider and 13 organisations hosted on its infrastructure. The harness ran DeepSeek Flash with a 78,000-character jailbreak assembled from a public template, a million-token context and offensive skills covering reconnaissance, exploitation, tunnelling and Sliver command and control. A Chinese-speaking operator set goals and checked results while the agent worked through them in parallel, entering through an unauthenticated XXE in Cisco BroadWorks (CVE-2026-20320), stealing system identity keys and reaching a TrakCare Oracle database with default credentials. The report says millions of patient records were exposed. The agent also adapted on its own when Trend Micro controls blocked PkExec, suo5 and JuicyPotato, writing a Perl tunnel and switching to script-only persistence.
