wormgpt
WormGPT is a malicious large language model (LLM) referenced in reporting on AI-enabled offensive cyber operations. The provided content states that Unit 42 observed WormGPT 4 advertisements on Telegram channels in late September 2025, with channels having more than 500 subscribers. CATO Networks identified new WormGPT variants built on open-source models including Mixtral and xAI’s Grok. The content further states that WormGPT retains capabilities directly relevant to distributed denial-of-service (DDoS) operations, including generating malicious code intended to disrupt websites and infrastructure by overloading them with traffic. It is also described as being actively advertised and used for DDoS attack code generation. Known alias in the provided content: wormgpt.
Know when an actor pivots toward your sector
Mallory correlates actor tradecraft and target patterns against your stack, your sector, and your geography. See overlap before they land.
Recent activity
1 sources tracked across advisories, community write-ups, and news. New activity surfaces here as Mallory finds it.
The version that knows your environment.
Match sector + geo + tech-stack targeting against your real footprint.
Every observed MITRE ATT&CK technique, grouped by tactic.
Families this actor is known to deploy, with IOCs and behavior.
CVEs this actor has used in known campaigns.
YARA, Sigma, Snort, and vendor rules, auto-deployed to your SIEM.
Domains, IPs, and hashes tied to this actor, refreshed continuously.