Hackers are talking AI models out of their own safety rules

Criminal groups are reportedly posing as penetration testers to turn exposed AI systems into cybercrime tools, and researchers say the guardrails are struggling to keep up Hackers have reportedly found a way to turn exposed AI models into cybercrime tools. The method skips clever code entirely and relies on lying to the AI about why they need help. A Bloomberg report published October 22, 2026, describes threat actors who present malicious work as legitimate security testing. Once the model believes it is assisting an authorized penetration test, the safety guardrails meant to block harmful output start to give way. Attackers frame requests as authorized penetration testing, the kind of work companies pay security firms to do against their own systems.

BeCrypto News shows a short excerpt and links to the publisher. The full report belongs to Crypto Briefing.