Fully Autonomous Agentic Attacks Are Three Months Away, Google Warns

LowInfosecurity Magazine·

At a glance

Severity
Low
Used in attacks
No flaws named
Vendors and products
Google
Reported by
1 outlet

Google expects sophisticated, fully autonomous agentic attacks to emerge in the next three to six months after observing a “paradigm shift” in the use of pen-testing frameworks like ARTEX in the past quarter.

The tech giant’s Google Threat Intelligence Group (GTIG) shared the news in its latest quarterly GTIG AI Threat Tracker published on November 16.

Compiled from Mandiant incident response telemetry, global threat actor tracking and live platform defenses, the report warned that ARTEX and open source, multi-agent frameworks such as CAIRN, CyberStrikeAI and PentAGI, are increasingly popular among threat actors.

Groups are also experimenting with custom-built harnesses, it added.

Read more on ARTEX: Microsoft: Chinese State Actor Used AI to Compromise ConnectWise Tenants.

Frameworks like ARTEX effectively manage a collection of sub-agents to plan, execute and adapt across multiple kill chain stages including reconnaissance and scanning, initial access, persistence and privilege escalation, internal reconnaissance and lateral movement, and completion of objectives.

“While the mechanics of the intrusions remain the same, such as using compromised credentials and targeting unpatched systems, the speed and scale at which frameworks can exploit these known weaknesses introduces a new defensive challenge,” the report explained.

“These frameworks share several core capabilities: discovering and exploiting low-complexity vulnerabilities, using LLMs to generate single-use payloads on-demand, and using real-time execution feedback to dynamically adjust tactics.”

Attacks Are Easy to Spot

GTIG said the “low barrier to entry, ease of integrating new exploits and massive scaling potential” is going to make such frameworks an enduringly popular choice for both cybercrime and nation state groups.

“Concurrently, as capabilities evolve, we suspect these operations will continue to move further along the autonomous scale, approaching fully agentic intrusions,” it added.

Threat actors are currently trading stealth for velocity, meaning that attacks generate plenty of forensic signals, “recognizable identifiers” and “code-level traces,” which can help defenders to detect and mitigate, the report noted. However, stealth will certainly increase going forward, it warned.

Sally Vincent, senior threat research engineer at Exabeam, argued that better behavioral monitoring by SOC teams could help to spot and block such threats by flagging unfamiliar tool use or unusual data access.

“It can also identify changes in activity volume. These changes can help expose an attack even when the attacker uses legitimate tools and valid credentials,” she added.

Google said its security operations (SecOps) team has deployed specialized behavioral and volumetric rulepacks to detect use of ARTEX. Mandiant has also released a hardening guide and defensive framework designed to help organizations counter the “speed and scale advantage” of AI-powered attackers.

Just last week, the FBI warned of the growing use of ARTEX in attacks, with South Korean financial institutions among the many victims.

Originally published by Infosecurity Magazine. © Infosecurity Magazine.

Fastnexa security experts

Dealing with this in your own company?

If this story touches software, suppliers or systems you use, a Fastnexa security expert can tell you what it means for you and what to do first.

Book a 30-min callWhatsApp us

Think you’ve already been hit? Don’t wait on a form: call or WhatsApp +1 (732) 454 2616. We reply within 1 hour, 24/7. Emergency help →

Coverage

One outlet has carried this so far.

  1. Infosecurity Magazine ↗Established SourceFirst reported

    2026-11-17 09:30 UTC

Related stories