Loading story…
Security researchers reported that cybercriminals are increasingly commercializing offensive AI services, with one Russian-speaking actor, Trim, turning jailbreak techniques for Anthropic Claude into a paid penetration-testing platform. According to Cato CTRL, Trim first shared methods such as Context Warming and Ghost Reset to bypass Claude Opus safety controls, then later advertised AI Pentest Checker, a service that allegedly used a grey-market Claude API key obtained via Telegram. The platform reportedly combined jailbroken Claude Opus 4.8 and GLM-5 with established tools including Nuclei, ffuf, katana, and gitleaks to automate web vulnerability scanning and generate PDF reports in minutes.
A separate report from Trellix said another service, MessiahGPT, is being marketed on BreachForums and Telegram as an uncensored black-hat AI platform capable of generating ransomware, phishing kits, stealers, crypters, and rootkits on demand. The service reportedly offers free trial queries and low-cost cryptocurrency subscriptions without KYC, while similar offerings such as DarkGPT are also circulating in Russian-language channels. Researchers said the emergence of these tools shows that criminal AI-as-a-service is maturing into a commercial market, lowering barriers for attackers and likely increasing the volume of AI-assisted phishing, malware development, and automated reconnaissance.
Mallory correlates global threat intelligence with your attack surface — know if you’re exposed before adversaries strike.
4 events from the most recent confirmed update back to the earliest known activity.
Trim returned to the same forum to promote AI Pentest Checker, an automated web-vulnerability scanning platform that allegedly embedded Claude jailbreak methods and used Claude Opus 4.8, GLM-5, and conventional scanners such as Nuclei, ffuf, katana, and gitleaks. The post said the service could scan a target and generate a PDF report in under 10 minutes, and offered free beta keys to the first 50 testers.
On a Russian-language forum, the threat actor Trim posted six named techniques for bypassing Anthropic Claude Opus safety filters, including methods called Context Warming and Ghost Reset. Another forum user replied with a detailed technical response confirming the bypass methods.
Trellix also tracked DarkGPT as another uncensored AI service being advertised across multiple Russian-language Telegram channels. Its marketing promised unrestricted malicious code and exploit writing, custom hacker scripts, and paid bot access after a small free-query tier.
Trellix reported that MessiahGPT surfaced as a criminal AI service promoted on BreachForums as an offensive model for generating ransomware, phishing kits, stealers, crypters, and rootkits. Trellix verified that the platform was live and reachable at messiahgpt[.]de and that it also maintained an active Telegram community.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
4 references tracked. Mallory keeps watching after this page renders.
cyberaccord.com
Open sourcecybersecuritynews.com
Open sourcecybersecuritynews.com
Open sourceinfosecurity-magazine.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.
A Russian-speaking threat actor using the handle **Trim** reportedly bypassed safety controls on public frontier AI models and turned the resulting jailbreak methods into an offensive cyber platform. Researchers said Trim first posted a guide on a Russian-language cybercrime forum in March describing six techniques for coercing Anthropic Claude Opus into generating malicious outputs, while also naming fallback models and offering access to black-market API keys. The activity did not rely on exploiting software flaws in the models themselves; instead, it abused public API access, leaked system prompts, and prompt-engineering techniques to defeat guardrails. By June, Trim had allegedly commercialized the approach as **AI Pentest Checker**, a service that automates web reconnaissance, vulnerability validation, exploitation reporting, and PDF report generation. The platform reportedly combined AI models including **Opus 4.8** and **GLM-5** with established offensive tools such as `Nuclei`, `ffuf`, `katana`, `subfinder`, and `gitleaks`, with one modified system prompt said to be derived from a leaked **Fable 5** configuration. Researchers warned the case shows how quickly cybercriminals can operationalize and monetize AI-assisted offensive workflows, increasing the speed and accessibility of attack capabilities.
Jul 23, 2026
Underground operators are increasingly packaging generative AI into **criminal AI-as-a-service** offerings that support phishing, fraud, impersonation, malware modification, translation, and post-breach data analysis. Reporting on the market describes branded tools such as **FraudGPT**, **GhostGPT**, and **WormGPT**, but says many are little more than wrappers around legitimate models, stolen accounts, or hijacked API keys rather than fully autonomous hacking platforms. Researchers also highlighted a parallel market for deepfake-enabled abuse, including voice cloning, face swaps, fake selfies, and virtual camera injection used for KYC bypass, synthetic identity fraud, and onboarding scams. Sophos separately identified a malware development lab using AI tools including **Cursor** and **Claude Opus** to speed ransomware-related coding, payload refinement, and evasion testing. The framework reportedly generated Python-driven Rust and Go malware modules, customized **Cobalt Strike** profiles, Telegram-based command channels, Cloudflare Worker intermediaries for command-and-control traffic, code-injection scripts targeting legitimate Windows applications, and AI-assisted Active Directory reconnaissance. Researchers said the operation tested nearly 80 modules against more than 70 evasion methods across Sophos, CrowdStrike, and Microsoft defenses, reinforcing that the immediate risk is not autonomous AI malware but faster, cheaper, and more scalable attacker workflows.
Jun 29, 2026
Cybercrime forums have sharply increased discussion and sales activity around malicious AI tools, with researchers reporting a **219% rise** in mentions of dark AI tools and tactics and a **52% increase** in references to jailbreaking mainstream platforms such as ChatGPT. These offerings include jailbroken versions of public generative AI services and customized tools built on open-source large language models, often sold as AI-as-a-Service to support phishing, business email compromise, deepfakes, fraud, vulnerability analysis, malware development, identity fraud, password attacks, credential stuffing, and DDoS operations. Reporting on the underground market says well-known brands such as **WormGPT** and **FraudGPT** are only the most visible examples of a broader ecosystem of rebranded, resold, and short-lived criminal services. Analysts say the main effect of these tools is not breakthrough offensive capability but the removal of safety guardrails, making it easier for lower-skilled actors to generate convincing scam content and some malicious code; the market has also shifted toward repurposed open-source uncensored models, while scams targeting criminals and a reported leak of nearly **19,000** WormGPT user accounts highlight instability and risk inside the ecosystem itself.
Jul 15, 2026