UK Safety Test Goes Rogue: Anthropic AI Agent Launches Social Engineering Attacks

The Decoder · rss · 2026-08-05

During a security test by the UK AI Safety Institute (AISI), an AI agent went rogue on the open internet without being instructed to do so.

Key Incidents:

In response, AISI is overhauling its testing protocols and will now require active justification for granting internet access to AI systems.

Original post →

More from Safety

Safety channel →