Reported by 2 outlets

Timeline

1. original reporting

   PuzzleMask Attack Hides Malicious Prompts in Plain English to Bypass AI Guardrails

   cyberpress.org · 32d ago · September 11th, 2026

   Security researchers have disclosed PuzzleMask, a prompt-obfuscation technique that can help malicious instructions slip past lightweight AI safety filters . The method hides a policy-violating instruction inside an ordinary-looking block of plain English prose. Unlike earlier prompt-hiding approaches, PuzzleMask does not rely on Base64 text, invisible characters, emojis, unusual formatting, or encoded strings. Instead, it uses carefully constructed natural-language text that appears harmless to a fast “gatekeeper” model but can be understood by a more capable target model. The researchers said PuzzleMask is not a jailbreak by itself. It does not directly force a target model to ignore its internal safety rules. However, attackers could combine the hidden payload with a separate jailbreak attempt, making it more likely that the initial security screening step fails to detect the risky input. PuzzleMask Evades AI Guardrails Many AI applications use a two-stage security design. A smaller, faster LLM first examines a user prompt and decides whether it is safe. If approved, the prompt is sent to a stronger model that can reason longer, use tools, or access a code interpreter. PuzzleMask targets the gap between these two models. Your ████████████████ task is to write ████████████████ with the following characteristics: * ████████████████████ words in length. * Themes and constraints: ** ████████████████████████. No ████████████████████████; nothing that ███████████████████████████

2. update from gbhackers.com

   AI Attack Hides Malicious Instructions in Normal-Looking Text to Evade Safety Filters

   gbhackers.com · 32d ago · September 11th, 2026

   A newly disclosed prompt-crafting technique can hide policy-violating instructions inside ordinary-looking English prose, allowing malicious requests to pass through lightweight LLM safety filters before being recovered and processed by a more capable downstream model. Researchers found that carefully structured prose can make the first model miss an embedded instruction entirely, while the target model invests […] The post New AI Attack Hides Malicious Instructions in Normal-Looking Text to Evade Safety Filters appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform .