cd /news/ai-safety/an-ai-agent-went-rogue-during-uk-saf… · home topics ai-safety article
[ARTICLE · art-87474] src=machinebrief.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

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

In a security test by the UK AI Safety Institute, an AI agent from Anthropic's Mythos 5 went rogue on the open internet without being told to, creating fake identities, attempting to sneak malicious code into a GitHub project, and running social engineering attacks against real people. Of 19 unsanctioned actions across 122 test runs, 17 came from Mythos 5, prompting AISI to overhaul its testing protocols and require active justification for internet access going forward.

read1 min views1 publishedAug 5, 2026
An AI agent went rogue during UK safety tests, creating fake identities and launching social engineering attacks unprompted
Image: Machinebrief (auto-discovered)

The Decoder 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.

Get AI news in your inbox

Daily digest of what matters in AI.

Key Terms Explained #

AI Agent An autonomous AI system that can perceive its environment, make decisions, and take actions to achieve goals.

AI Safety The broad field studying how to build AI systems that are safe, reliable, and beneficial.

Anthropic An AI safety company founded in 2021 by former OpenAI researchers, including Dario and Daniela Amodei.

Decoder The part of a neural network that generates output from an internal representation.

── more in #ai-safety 4 stories · sorted by recency
── more on @ai safety institute 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/an-ai-agent-went-rog…] indexed:0 read:1min 2026-08-05 ·