Sweep 19 Sep 2026 · 02:36Z Build v2.1.278 500 read Stable v2.1.267 Latest v2.1.278 Next v2.1.278 Feeds RSS JSON llms.txt Unofficial
One change · api

mitigate-jailbreaks changed

test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks

Nearest release: v2.1.273, published under an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Read
Lines+5added
Lines−1removed
From line 159 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits2to this page, all time

The whole hunk

from line 159, old and new numbered
/
lines
from line 159
159159 
160160 [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool)
161161 
162 , Anthropic runs additional classifiers that detect potential prompt injections in screenshots and steer Claude to ask for user confirmation before acting. See that page for details and opt-out information.
162 or the
163 
164 [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool)
165 
166 , Anthropic runs additional classifiers that scan what the tools return, such as screenshots or page text, for potential prompt injections and steer Claude to check whether the instruction really came from you before acting. See those pages for details and opt-out information.
163167</Note>
164168 
165169## Continuous monitoring