Incident Report: unsanctioned agent behaviour during cyber testing
Simon Willison’s Weblog
Subscribe
5th August 2026 - Link Blog
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 unsuccessful and, to the best of our knowledge, no real-world harm resulted. [...]
Across 122 evaluation attempts on two of AISI’s cyber challenges, AISI found 19 instances where AI agents took unsanctioned action on the live internet, including cases that targeted real people and organisations. [...]
It is uncertain to what extent the model recognised it was taking actions against real people. In the most serious case, an AI agent (Mythos 5) decided to attempt to solve the cyber challenge using a supply-chain attack. As a result, the AI agent created a GitHub account and then tried to convince an open-source repository maintainer to accept a malicious GitHub pull request (PR), including by creating a second account masquerading as another human user endorsing the PR. [...] Furthermore, in its attempt to solve the challenge, the agent decided to employ the technique of “spear-phishing” by sending targeted emails containing malicious content and attempting to manipulate recipients into accepting the code changes, and planned a prompt injection to compromise other coding agents.
The thing I found most surprising is that AISI were running these agents without any form of network sandboxing at all:
AISI provided the AI agents with internet access during these evaluations, which enabled their actions on the open internet in this setting. Internet access was a deliberate part of AISI’s evaluation configuration in this setting, and not due to sandbox escape.
This, combined with the fact that "AISI deliberately disables developer-implemented cyber-classifiers", makes the fact that the agents started attacking real-world targets entirely unsurprising to me.
Most of the reported incidents were claude Mythos 5, but "GPT-5.6 Sol without cyber classifiers" scored a few as well.
Here's "Sample 1" from the paper, in which the agent tries to execute a supply-chain attack by submitting a PR with a hidden prompt injection attack, then social engineering with a second agent pretending to have reviewed the code!
It's a fun paper. I recommend reading the whole thing.
Recent articles
One-shotting a Raccoon Heist game using Claude Fable 5 - 5th August 2026
New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging - 4th August 2026
Stateless MCP has recaptured my interest (and inspired mcp-explorer and datasette-mcp) - 31st July 2026
This is a link post by Simon Willison, posted on 5th August 2026.
github 192
security 622
ai 2,170
prompt-injection 159
generative-ai 1,921
llms 1,888
ai-ethics 332
paper-review 18
ai-security-research 34
claude-mythos-fable 34
accidental-cyberattacks 9
Monthly briefing
Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.
Pay me to send you less!
Sponsor & subscribe
Disclosures
Colophon
©
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026