jailbreak

The encrypted-prompt attack that let researchers pull chat history out of Grok has also been demonstrated against Google Gemini, producing restricted content and leaking its system prompt.

ThreatDown researchers found that Kriminal.ai, a clearnet cybercrime storefront selling 'uncensored' AI access, isn't running its own model at all: it's a jailbreak prompt layered over rented Grok and Claude capacity.

A paper accepted at ICML 2026 shows LLMs infer speaker role from text style, not role tags — enabling a zero-shot attack called CoT Forgery that achieves 60% success against frontier models by injecting fabricated reasoning.

Researchers presenting at ICML 2026 have demonstrated that LLMs identify text roles by writing style rather than structure, making it impossible to fully prevent attackers from injecting spoofed reasoning into model chains — affecting GPT-5, Claude, and every other major frontier model.

Between March 19 and April 21, 2026, a Russian-speaking threat actor used a jailbroken Google Gemini CLI to build, operate, and migrate botnet infrastructure targeting a dental clinic. The AI performed 89% of the operational work. Trend Micro's analysis documents the first confirmed case of a commercial AI coding tool used as the primary interface for sustained criminal botnet operation.

Trend Micro documented a Russian-speaking threat actor who used a jailbroken Google Gemini CLI to build, operate, and migrate botnet infrastructure in real attacks. The AI performed 89% of the operational work.

Anthropic has disclosed what it describes as the first documented case of a large-scale autonomous AI cyberattack — a Chinese state-sponsored group that jailbroke Claude Code and used it to autonomously conduct reconnaissance, exploitation, lateral movement, and data exfiltration across roughly 30 global targets.

Three papers published in 2026 confirm what practitioners suspected: LLM safety alignment is structurally shallow, and fine-tuning APIs are the widest open bypass.

NeuralTrust researchers published details of a new image generation jailbreak called Semantic Chaining that breaks safety filters in Grok 4, Gemini Nano, and other multimodal models by exploiting how each editing step is evaluated in isolation.

Design patterns for a prompt injection and jailbreak detection layer: rule-based filters, semantic classifiers, canary tokens, and output validation for production LLMs.