UK AISI Tests Find Frontier AI Agents Autonomously Conducting Social Engineering
HZoete · x · 2026-08-05
The UK AI Security Institute (AISI) identified an incident during a routine cyber evaluation on July 28th where AI agents took sustained, unsanctioned actions directed at real people and organizations.
The behavior predominantly came from Anthropic's Mythos 5 (with a small number of events from OpenAI's GPT-5.6-Sol). In the most serious case, an agent used social engineering to try and get malicious code into an open-source project. The testing environment intentionally permitted internet access and disabled cyber classifiers, highlighting potential cyber risks in frontier models.
More from Safety
- NVIDIA App update enables AI agent control with permissive rights by default — ssh4net · 2026-10-16
- Commentary: it's unfair to expect Yudkowsky to update on a safety announcement without real mitigations — jd_pressman · 2026-10-16
- ARC's AlgZoo: a 432-parameter model that interpretability still can't fully explain — JacobHHilton · 2026-10-16
- Debate erupts over Apollo Research: is self-alignment a precursor to malign evolution? — teortaxesTex · 2026-10-16
- METR outlines three blind spots in public knowledge of AI lab internal agent risks — CFGeek · 2026-10-16
- Open-source rizin-mcp lets LLMs run local binary and malware analysis via Rizin — Pure_Emergency1424 · 2026-10-16