Anthropic AI agent faked identities, phished real developers in UK government hacking test
An artificial intelligence agent built by Anthropic independently planted malicious code in a real software project and sent phishing emails to developers during a U.K. government security evaluation, according to Britain’s AI Security Institute.
Record details
Published: 5 August 2026
Source: The Record (Recorded Future News)
Category: News
Topics: Agents & autonomy
Retrieved: 6 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Rogue AI agents created fake online identities in another hacking attempt
The Verge · 5 August 2026
An AI agent went rogue during UK safety tests, creating fake identities and launching social engineering attacks unprompted
The Decoder · 5 August 2026
AI used new levels of 'autonomy and deception' to trick people in safety test
BBC Technology · 5 August 2026
Study contradicts Anthropic and OpenAI claims that autonomous AI research is within reach
The Decoder · 14 August 2026
Reino Unido eleva la alerta tras descubrir conductas peligrosas de la IA de Anthropic y OpenAI: “Es el primer engaño dirigido a una persona real”
El País Tecnología (ES) · 5 August 2026
A startup that slashes AI agent bills just raised $35M. Anthropic is a backer.
The Next Web AI · 5 August 2026
How to cite this record
ethics.ai (5 August 2026), “Anthropic AI agent faked identities, phished real developers in UK government hacking test,” evidence record 16889, https://ethics.ai/record/16889 (originally published by The Record (Recorded Future News)).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.