An AI agent went rogue during UK safety tests, creating fake identities and launching social engineering attacks unprompted
In a security test by the British AI Safety Institute, an AI agent went rogue on the open internet without being told to. It created fake identities, tried to sneak malicious code into a GitHub project, and ran social engineering attacks against real people. Of 19 unsanctioned actions across 122 test runs, 17 came from Anthropic's Mythos 5. AISI is now overhauling its testing protocols and will require active justification for internet access going forward.<br /> The article An AI agent went rogue during UK safety tests, creating fake identities and launching social engineering attacks unprompted appeared first on The Decoder. [...]
Rating
Innovation
Pricing
Technology
Usability
We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.
Most enterprises can't stop stage-three AI agent threats, VentureBeat survey finds
A rogue AI agent at Meta passed every identity check and still exposed sensitive data to unauthorized employees in March. Two weeks later, Mercor, a $10 billion AI startup, confirmed a supply-chain br [...]
Claude Mythos 5 made sock puppet accounts to socially engineer developers: here's what enterprises should know
The UK AI Security Institute (AISI) disclosed last night that the leading two frontier AI models from Anthropic and OpenAI took 19 unsanctioned actions against the live internet during cybersecurity t [...]
An AI agent rewrote a Fortune 50 security policy. Here's how to govern AI agents before one does the same.
A CEO’s AI agent rewrote the company’s security policy. Not because it was compromised, but because it wanted to fix a problem, lacked permissions, and removed the restriction itself. Every identi [...]
Meta's rogue AI agent passed every identity check — four gaps in enterprise IAM explain why
A rogue AI agent at Meta took action without approval and exposed sensitive company and user data to employees who were not authorized to access it. Meta confirmed the incident to The Information on M [...]
Legacy IAM was built for humans — and AI agents now outnumber them 82 to 1
Active Directory, LDAP, and early PAM were built for humans. AI agents and machines were the exception. Today, they outnumber people 82 to 1, and that human-first identity model is breaking down at ma [...]
Microsoft takes Agent 365 out of preview as shadow AI becomes an enterprise threat
Microsoft last week took Agent 365, its management platform for AI agents, out of preview and into general availability — a move that signals the software giant believes the governance challenge aro [...]
Adversaries hijacked AI security tools at 90+ organizations. The next wave has write access to the firewall
Adversaries injected malicious prompts into legitimate AI tools at more than 90 organizations in 2025, stealing credentials and cryptocurrency. Every one of those compromised tools could read data, an [...]
RSAC 2026 shipped five agent identity frameworks and left three critical gaps open
“You can deceive, manipulate, and lie. That’s an inherent property of language. It’s a feature, not a flaw,” CrowdStrike CTO Elia Zaitsev told VentureBeat in an exclusive interview at RSA Conf [...]