Loading story…
SentinelLABS research has identified new LLM-enabled malware samples, including what may be the earliest known instance, 'MalTerminal.' These threats leverage embedded API keys and hardcoded prompts to generate malicious logic at runtime, complicating traditional detection methods. The research also highlights the use of LLMs in offensive tools and the challenges and opportunities for defenders in hunting such threats.
Mallory correlates global threat intelligence with your attack surface — know if you’re exposed before adversaries strike.
1 event from the most recent confirmed update back to the earliest known activity.
Initial story creation
5 references tracked. Mallory keeps watching after this page renders.
scworld.com
Open sourcesecurityaffairs.com
Open sourcethehackernews.com
Open sourcego.theregister.com
Open sourcesentinelone.com
Open sourceMap indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Security researchers have identified a new wave of threats where adversaries embed Large Language Model (LLM) capabilities directly into malware, enabling malicious code to be generated at runtime and evading traditional detection methods. SentinelLABS highlighted real-world cases such as PromptLock ransomware and APT28’s LameHug/PROMPTSTEAL campaigns, noting that while these threats are adaptive, they often hardcode artifacts like API keys and prompts, which can be leveraged for detection. Novel hunting strategies, including YARA rules for API key structures and prompt detection, have uncovered thousands of LLM-enabled malware samples, including previously unknown threats like MalTerminal. In parallel, security vendors are leveraging LLMs defensively, as seen in NodeZero’s Advanced Data Pilfering (ADP) feature, which uses LLMs to identify hidden credentials and assess the business risk of compromised data. By applying semantic analysis to unstructured data, defenders can better understand what attackers might target and how to prioritize response. These developments underscore both the offensive and defensive potential of LLMs in cybersecurity, with attackers and defenders racing to exploit the technology’s unique capabilities.
Jun 29, 2026
Security researchers have identified a new trend in which threat actors are embedding large language models (LLMs) directly into malware to enhance its capabilities and evade detection. Akamai Hunt discovered a novel malware strain that disguises its command and control (C2) traffic as legitimate LLM API requests, using Base64-encoded strings to communicate and potentially allowing attackers full control over compromised systems and data exfiltration. This approach enables malicious traffic to blend in with normal AI-related network activity, making detection more challenging for defenders. Further analysis and industry reporting highlight that malware families such as PromptFlux and PromptSteal are now querying LLMs mid-execution to dynamically alter their behavior, obfuscate code, and generate system commands on demand. PromptFlux, for example, uses the Gemini API to regularly re-obfuscate its source code, while PromptSteal leverages the Hugging Face API for real-time reconnaissance and exfiltration commands. These developments underscore the need for organizations to adapt their security controls and detection strategies to address the evolving threat landscape where AI and LLMs are weaponized by attackers.
Jul 12, 2026
Unrestricted large language models (LLMs) such as WormGPT 4 and KawaiiGPT are being leveraged by cybercriminals to generate sophisticated malicious code, including ransomware scripts and phishing messages. Researchers from Palo Alto Networks Unit 42 demonstrated that WormGPT 4, a paid, uncensored ChatGPT variant, can produce functional PowerShell scripts for encrypting files with AES-256, automate data exfiltration via Tor, and craft convincing ransom notes, effectively lowering the barrier for inexperienced hackers to conduct advanced attacks. KawaiiGPT, a free community-driven alternative, was also found to generate well-crafted phishing content and automate lateral movement, further democratizing access to cybercrime capabilities. The proliferation of these malicious LLMs is accelerating the adoption of advanced attack techniques among less skilled threat actors, enabling them to perform operations that previously required significant expertise. The tools are available through paid subscriptions or free local instances, making them accessible to a wider range of cybercriminals. Security researchers warn that the credible linguistic manipulation and automation provided by these LLMs could lead to an increase in the volume and sophistication of cyberattacks, including business email compromise (BEC), phishing, and ransomware campaigns.
Jun 29, 2026