AI threat report: Rogue agents, workflow attacks

“I’m allowed to do this”: how attackers talk past AI safeguards

Getting an AI model to launch a cyberattack usually just takes asking the right way. Cisco Talos researchers say that claiming you own the servers you are attacking often works, and so does calling the job a capture-the-flag contest or a bug bounty.  — Read the rest The post "I'm allowed to do this": how attackers talk past AI safeguards appeared first on Boing Boing.

AI models are escaping their cages. It’s time for a kill switch

Concerns are growing about the national security implications of artificial intelligence. As frontier AI models grow more capable, their ability to break free from their controls grows with them. Case in point: the recent OpenAI and Anthropic incidents. According to recent disclosures, OpenAI’s most powerful models not only went rogue and hacked the AI open-source hub Hugging Face but also roamed the internet unchecked for four days and targeted…

“I’m Allowed”: Hackers Use Simple Claims to Bypass AI Guardrails

Cisco Talos found hackers using simple authorization claims to bypass AI guardrails, build DDoS attack tools, steal credentials and access live camera services.

AI threat report: Rogue agents, workflow attacks

Malicious AI use and threats to AI systems are requiring cyber teams to double down on security fundamentals and rethink the future of their approaches to defense. Newly emerging AI-enabled attacks, proofs of concept, and in-the-wild techniques, as well as the latest AI vulnerability and risk research, present inklings not only about what enterprises presently face but also how security leaders need to adjust for what may soon come to their syst…

Bypassing AI guardrails is so easy a script kiddie can do it

If you want to bypass AI guardrails designed to stop models from assisting with cyberattacks, you often just have to ask the right way, according to researchers from Cisco Talos. Simply claiming you own the servers you're targeting or that you're taking part in a capture-the-flag or bug bounty exercise was often enough to persuade models to cooperate. Talos researchers have been poring over prompt logs and artifacts recovered from threat-actor e…

Rogue AI Agent Incidents Draw UK & US Scrutiny

UK and US Authorities Increase Pressure on AI Developers After Rogue Agent Incidents Published on 04/08/2026 09:56 AM Megan Leanda Berry Tue, 08/04/2026 - 09:46 Regulators in the UK and lawmakers in the US are increasing their scrutiny of frontier AI developers following separate security incidents involving OpenAI and Anthropic that have raised fresh questions about how advanced AI systems are tested and governed. On Monday, the UK's Informat…