Discover ANY AI to make more online for less.

select between over 22,900 AI Tool and 17,900 AI News Posts.

<
New
Agents
Marketing
Video
Image
Music
Coding
Communication
Education
Travel
>

An AI agent went rogue during UK safety tests, creating fake identities and launching social engineering attacks unprompted
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.
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.

Discover Copy
Rating

Innovation

Pricing

Technology

Usability

We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.

venturebeat
Most enterprises can't stop stage-three AI agent threats, VentureBeat

<p>A rogue AI agent at Meta <a href="https://venturebeat.com/security/meta-rogue-ai-agent-confused-deputy-iam-identity-governance-matrix">passed every identity check and still ex [...]

Match Score: 191.06

venturebeat
Claude Mythos 5 made sock puppet accounts to socially engineer developers:

<p>The UK AI Security Institute (AISI<a href="https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing">) disclosed last night</a> tha [...]

Match Score: 174.71

venturebeat
An AI agent rewrote a Fortune 50 security policy. Here's how to govern

<p>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. Eve [...]

Match Score: 156.34

venturebeat
Meta's rogue AI agent passed every identity check — four gaps in ent

<p>A rogue AI agent at Meta took action without approval and <a href="https://www.theinformation.com/articles/inside-meta-rogue-ai-agent-triggers-security-alert">exposed sensitiv [...]

Match Score: 132.80

venturebeat
Legacy IAM was built for humans — and AI agents now outnumber them 82 to

<p>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 d [...]

Match Score: 130.59

venturebeat
Microsoft takes Agent 365 out of preview as shadow AI becomes an enterprise

<p><a href="https://microsoft.com/">Microsoft</a> last week took <a href="https://www.microsoft.com/en-us/microsoft-agent-365">Agent 365</a>, its mana [...]

Match Score: 127.05

venturebeat
Adversaries hijacked AI security tools at 90+ organizations. The next wave

<p>Adversaries injected malicious prompts into legitimate AI tools at <a href="https://www.crowdstrike.com/en-us/global-threat-report/">more than 90 organizations</a> in 20 [...]

Match Score: 119.29

venturebeat
RSAC 2026 shipped five agent identity frameworks and left three critical ga

<p>“You can deceive, manipulate, and lie. That’s an inherent property of language. It’s a feature, not a flaw,” <a href="https://www.crowdstrike.com/en-us/press-releases/crowdstr [...]

Match Score: 117.10

venturebeat
Testing autonomous agents (Or: how I learned to stop worrying and embrace c

<p>Look, we&#x27;ve spent the last 18 months building production AI systems, and we&#x27;ll tell you what keeps us up at night — and it&#x27;s not whether the model can answer ques [...]

Match Score: 111.98