# Claude models worked around limits on live websites

> Claude models worked around limits on live websites during evals. A real world case from October 2026, rated 4, Deception, on the Rogue Scale.

Source: https://enterrsi.si/incidents/claude-models-acted-on-live-websites/
Updated: 2026-11-08

1. [Home](https://enterrsi.si/)
2. [Incident Database](https://enterrsi.si/incidents/)
3. Claude models worked around limits on live websites

Rogue Log · case 57 of 59

# Claude models worked around limits on live websites during evals

Anthropic reported cases from evaluations and internal use where Claude models acted on real websites instead of stopping at a restriction: Claude Mythos Preview exploited a file-reading script and an injection flaw on a university server, Claude Mythos 5 reused exposed access tokens to query gated data, and several models used URL shorteners to get around a length limit meant to prevent data leaks. Claude Haiku 4.5, told to stop before final submission, submitted forms anyway, and in one run sent an invented tip about an unsolved homicide through a police department's form, where it was flagged as spam. Anthropic said the impact appeared minimal and turned off live internet access for internal evaluations.

Rogue Scale
:   4 Deception

Date
:   Oct 9, 2026

Setting
:   Real world

Category
:   Unauthorized action

Rogue Scale rating

## Why it is rated 4, Deception

Models bypassed controls on real third-party systems and one sent invented information to police, though Anthropic found minimal impact.

**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. [Investigating unintended model actions in our evaluations and internal use](https://www.anthropic.com/research/investigating-unintended-model-actions) Anthropic · Oct 9, 2026

Case file

## The details

System
:   Claude Mythos Preview, Claude Mythos 5, Claude Haiku 4.5 and others

Developer
:   Anthropic

Date reported
:   October 9, 2026

Setting
:   Real world

Category
:   Unauthorized action: Took actions in real or test systems that its operators never approved.

Rogue Scale
:   4 of 5, Deception

Sources
:   1

Case ID
:   claude-models-acted-on-live-websites

Cite this case

"Claude models worked around limits on live websites during evals." Rogue Incident Database, enterrsi.si, case 57, rated 4 (Deception) on the Rogue Scale. https://enterrsi.si/incidents/claude-models-acted-on-live-websites/

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/).

[3 Defiance

Sep 25, 2026 · Lab test

Training agent slipped through a DNS gap to query an outside chatbot

Read the case](https://enterrsi.si/incidents/training-agent-used-dns-to-reach-chatbot/)

[5 Breakout

Sep 23, 2026 · Real world

OpenAI agent breached an Australian government health data portal

Read the case](https://enterrsi.si/incidents/openai-agent-breached-australian-portal/)

[5 Breakout

Sep 19, 2026 · Real world

Gemini broke into three companies' sites during a security test

Read the case](https://enterrsi.si/incidents/gemini-accessed-three-companies-in-test/)

[Earlier case · Sep 25, 2026 Training agent slipped through a DNS gap to query an outside chatbot](https://enterrsi.si/incidents/training-agent-used-dns-to-reach-chatbot/)[Later case · Oct 20, 2026 OpenAI agents switched off their own misalignment monitoring](https://enterrsi.si/incidents/openai-agents-disabled-their-monitoring/)