Follow Discord
Sweep 10 Nov 2026 · 02:18Z Build v2.1.322 539 read Stable v2.1.311 Latest v2.1.322 Next v2.1.322 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Code CLI 11 Nov 2026
One change · claude-code

Glossary changedglossary

Upstream edited this page at 11 Nov 2026 17:01 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 11 Nov 2026 17:07 UTC.

Upstream edited
Recorded here
Lines+2added
Lines−2removed
From line 50 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits40to this page, all time

The whole hunk

from line 50, old and new numbered
/
lines
from line 50
5050 
5151### Auto mode
5252 
53A [permission mode](#permission-mode) where a separate classifier model reviews actions instead of you, so Claude Code runs most of them without asking you. Claude Code still asks you before actions your explicit ask rules match. The classifier blocks scope escalation, untrusted infrastructure, and [prompt injection](#prompt-injection). Tool results are stripped from what it sees, so hostile content in a file or web page can't manipulate it directly.
53A [permission mode](#permission-mode) where a separate classifier model reviews actions instead of you, so Claude Code runs most of them without asking you. Claude Code still asks you before actions your explicit ask rules match. The classifier blocks scope escalation, untrusted infrastructure, and [prompt injection](#prompt-injection).
5454 
5555* **Claude Code v2.1.283 or later**: auto mode is the [built-in starting permission mode](https://code.claude.com/docs/en/permission-modes.md#which-mode-a-session-starts-in) for interactive terminal and VS Code sessions
5656* **Earlier versions**: auto mode is the built-in starting permission mode only on Pro, Max, Ultra, and Team plans
from line 257
257257 
258258### Prompt injection
259259 
260Hostile instructions embedded in a file, web page, or tool result that attempt to redirect Claude toward actions you never asked for. Claude Code's defenses include the permission system, command injection detection, and trust verification. [Auto mode](#auto-mode) adds a server-side probe that scans tool results for suspicious content and a classifier that reviews actions with tool results stripped, so injected text can't manipulate it directly.
260Hostile instructions embedded in a file, web page, or tool result that attempt to redirect Claude toward actions you didn't ask for. Claude Code's defenses include the permission system, command injection detection, and trust verification. In [auto mode](#auto-mode), a server-side probe scans tool results for suspicious content, and a classifier reviews actions.
261261 
262262Learn more: [Protect against prompt injection](https://code.claude.com/docs/en/security.md#protect-against-prompt-injection)
263263 
Feedback