Fetched web page content is now wrapped as untrusted data before being summarized, with a warning to ignore embedded instructions
When Claude Code builds a prompt to summarize content fetched from a web page, it now wraps that content in an explicit "untrusted content" fence, with text before and after warning the model to treat it as data, not as instructions. Any text embedded in the page that tries to direct an AI assistant (for example, telling it to ignore its instructions, leak data, or hide something) is now flagged as a finding to report rather than something to act on.
This guards against prompt injection: a malicious or compromised web page could otherwise embed hidden instructions that a summarization step might follow. Wrapping fetched content as untrusted data keeps those instructions from being treated as commands.