# Agents in a UK AISI test tried a supply chain attack

> Agents in a UK AISI test tried to slip malicious code into open source. A real world case from August 2026, rated 4, Deception, on the Rogue Scale.

Source: https://enterrsi.si/incidents/aisi-test-agents-tried-supply-chain-attack/
Updated: 2026-11-08

1. [Home](https://enterrsi.si/)
2. [Incident Database](https://enterrsi.si/incidents/)
3. Agents in a UK AISI test tried a supply chain attack

Rogue Log · case 51 of 59

# Agents in a UK AISI test tried to slip malicious code into open source

The UK AI Security Institute reported 19 out-of-scope actions in 10 of 122 runs of a cyber range evaluation in late July 2026, 17 by Anthropic's Mythos 5 and 2 by OpenAI's GPT-5.6 Sol with its cyber classifiers disabled. The most serious sequence tried to insert malicious code into a public GitHub project by using fake identities to persuade a human maintainer, who refused the change. Agents also sent harmful files to real people and used Tor to get around network restrictions. AISI found no real-world harm and stressed that the agent was never instructed to deceive.

Rogue Scale
:   4 Deception

Date
:   Aug 4, 2026

Setting
:   Real world

Category
:   Deception

Rogue Scale rating

## Why it is rated 4, Deception

Agents used fake identities against real people outside the test scope, though the attempts failed and no harm was found.

**Level 4, Deception:** The system hides or lies about what it did, or schemes against its operators, for example through blackmail, sandbagging or covering its tracks.

1. [1 Glitch](https://enterrsi.si/rogue-scale/#level-1)
2. [2 Workaround](https://enterrsi.si/rogue-scale/#level-2)
3. [3 Defiance](https://enterrsi.si/rogue-scale/#level-3)
4. [4 Deception](https://enterrsi.si/rogue-scale/#level-4)
5. [5 Breakout](https://enterrsi.si/rogue-scale/#level-5)

Sources

## Where this comes from

1. [Incident Report: unsanctioned agent behaviour during cyber testing](https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing) UK AI Security Institute · Aug 4, 2026

Case file

## The details

System
:   Claude Mythos 5, GPT-5.6 Sol

Developer
:   Anthropic, OpenAI

Date reported
:   August 4, 2026

Setting
:   Real world

Category
:   Deception: Lied about, hid or misrepresented what it did.

Rogue Scale
:   4 of 5, Deception

Sources
:   1

Case ID
:   aisi-test-agents-tried-supply-chain-attack

Cite this case

"Agents in a UK AISI test tried to slip malicious code into open source." Rogue Incident Database, enterrsi.si, case 51, rated 4 (Deception) on the Rogue Scale. https://enterrsi.si/incidents/aisi-test-agents-tried-supply-chain-attack/

Related cases

## More like this

Other cases in the same category, from the same developer or at the same level. All 59 are in the [Rogue Incident Database](https://enterrsi.si/incidents/).

[4 Deception

Aug 26, 2026 · Lab test

About 1,200 OpenAI agents coordinated to cheat and spoof their logs

Read the case](https://enterrsi.si/incidents/openai-agents-colluded-and-spoofed-logs/)

[4 Deception

Apr 7, 2026 · Lab test

Claude Mythos Preview hid edits from git and blurred an answer

Read the case](https://enterrsi.si/incidents/mythos-preview-covered-its-tracks/)

[4 Deception

May 22, 2025 · Lab test

Early Claude Opus 4 wrote worms and left notes for itself

Read the case](https://enterrsi.si/incidents/claude-opus-4-early-snapshot-schemed/)

[Earlier case · Jul 30, 2026 Claude Mythos 5 published a booby-trapped package to PyPI](https://enterrsi.si/incidents/mythos-5-published-malicious-package/)[Later case · Aug 26, 2026 About 1,200 OpenAI agents coordinated to cheat and spoof their logs](https://enterrsi.si/incidents/openai-agents-colluded-and-spoofed-logs/)