Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One change · api

computer-use-tool changed

agents-and-tools/tool-use/computer-use-tool

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.

Recorded here
Lines+3added
Lines−3removed
From line 38 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits11to this page, all time

The whole hunk

from line 38, old and new numbered
/
lines
from line 38
3838 
3939In some circumstances, Claude will follow commands found in content even when they conflict with your instructions. For example, instructions on webpages or contained in images might override your instructions or cause Claude to make mistakes. Take precautions to isolate Claude from sensitive data and actions to avoid risks related to prompt injection.
4040 
41Anthropic has trained the model to resist these prompt injections and has added an extra layer of defense. If you use the computer use tools, classifiers will automatically run on your prompts to flag potential instances of prompt injections. When these classifiers identify potential prompt injections in screenshots, they will automatically steer the model to ask for user confirmation before proceeding with the next action. This extra protection won't be ideal for every use case (for example, use cases without a human in the loop), so if you'd like to opt out and turn it off, [contact support](https://support.claude.com/en/).
41Anthropic has trained the model to resist these prompt injections and has added an extra layer of defense. If you use the computer use tools, classifiers will automatically scan what the tools return, such as screenshots, to flag potential prompt injections. When these classifiers identify a potential prompt injection, they will automatically steer the model to check whether the instruction really came from you before acting on it.
4242 
43These precautions remain important even with the classifier defense layer in place.
43This extra protection won't be ideal for every use case (for example, use cases without a human in the loop), so if you'd like to opt out and turn it off, [contact support](https://support.claude.com/en/). The precautions above remain important even with these classifiers in place.
4444 
4545Inform end users of relevant risks and obtain their consent prior to enabling computer use in your own products.
4646