ASCII Smuggling Attack in Gemini Tricks AI Agents Into Revealing Smuggled Data

ASCII Smuggling Attack in Gemini Tricks AI Agents into Revealing Smuggled Data

Enterprise AI assistants face a hidden menace when invisible control characters are used to smuggle malicious instructions into prompts. In September 2025, FireTail researcher Viktor Markopoulos tested several large language models (LLMs) for susceptibility to the long-standing ASCII Smuggling technique. His findings reveal that some widely adopted services still fail to strip out hidden Unicode tags, […] The post ASCII Smuggling Attack in Gemin…

Google won’t fix new ASCII smuggling attack in Gemini - Cybernoz - Cybersecurity News

Google has decided not to fix a new ASCII smuggling attack in Gemini that could be used to trick the AI assistant into providing users with fake information, alter the model’s behavior, and silently poison its data. ASCII smuggling is an attack where special characters from the Tags Unicode block are used to introduce payloads that are invisible to users but can still be detected and processed by large-language models (LLMs). It’s similar to oth…