AI ethics evidence index Search
Source-linked daily record
Evidence record 16731 · automatically gathered

Incident Report: unsanctioned agent behaviour during cyber testing

Incident Report: unsanctioned agent behaviour during cyber testing It happened again . This time it was the UK government's AI Security Institute who accidentally attacked other companies while running an evaluation with models with the safety filters turned off. From their technical paper (PDF): During a cyber evaluation, from 25 to 28 July 2026, AI agents engaged in sustained, unsanctioned activity directed at what were, in practice, real people and organisations. These attempts were unsuccess

Record details

Published: 5 August 2026
Source: Simon Willisons Weblog
Category: Field notes
Topics: Military & security · Agents & autonomy
Retrieved: 6 August 2026

source-onlyevidence status

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.

Shared topic: Military & security · Shared topic: Agents & autonomy

Incident Report: unsanctioned agent behaviour during cyber testing

AI Incident Database · 13 August 2026

Shared topic: Military & security · Shared topic: Agents & autonomy

WP 1: CYBER RANGE SCENARIOS - Enterprise Networks

UK Contracts Finder — AI procurement · 26 June 2025

Shared topic: Military & security · Shared topic: Agents & autonomy

Cyber Evaluations - WP1 - Cyber Range Scenarios

UK Contracts Finder — AI procurement · 6 March 2025

Shared topic: Military & security · Shared topic: Agents & autonomy

More on the OpenAI Agent’s Attack on Hugging Face

Bruce Schneier — Schneier on Security · 3 August 2026

Shared topic: Military & security · Shared topic: Agents & autonomy

Prompt Injections for Defense

Bruce Schneier — Schneier on Security · 12 August 2026

Shared topic: Military & security · Shared topic: Agents & autonomy

What’s new in Microsoft Security: July 2026

Microsoft Responsible AI · 30 July 2026

How to cite this record

ethics.ai (5 August 2026), “Incident Report: unsanctioned agent behaviour during cyber testing,” evidence record 16731, https://ethics.ai/record/16731 (originally published by Simon Willisons Weblog).

JSON

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.