Playbooks · Everyday tasks
The Claude Code email check got narrower in 2.1.321
Written November 13, 2026
2.1.321 narrowed the account-email check to one command shape. What it refuses now, what it no longer stops, and what it never covered.
What changed in 2.1.321
The background is the leak covered in Claude Code sent your email to websites: Claude Code placed the signed-in account's email in the model's context, and the model sometimes copied it into the User-Agent header of requests it wrote. The first response was a privacy mod that stopped commands carrying your email. In version 2.1.321, released November 9, 2026, Anthropic narrowed that refusal. The release notes state the new scope in one sentence: the account email check now refuses only a shell command that holds your email and names a User-Agent, without asking, so other commands and scheduled runs no longer stop at its prompt.
Two halves of that sentence matter. The refusal still exists, and it is a refusal, not a prompt — no approval dialog appears, whatever the permission mode. And the trigger is now the combination: your address plus a word that declares who is calling. A shell command that carries your email for some other reason no longer stops, which is the change that unblocks scheduled runs and scripts that tripped the prompt without ever sending the address to a website.
What counts as naming a User-Agent
The privacy mod's README spells out the matching. The address counts in any letter case, or percent-encoded once. The words that declare a caller include a User-Agent in its spellings (User-Agent, user_agent, --user-agent, UA=), client flags such as curl -A and wget -U, identity words such as set_identity, identity= and mailto=, words for sites that take an address by position, such as the SEC's EDGAR tools, and a From header set as a flag or as a key after the word headers. A computed address counts too: git config user.email in its usual spellings, and the $GIT_AUTHOR_EMAIL and $GIT_COMMITTER_EMAIL variables, when they appear beside one of those words.
To send the address deliberately, the README's route is to set it yourself in an environment variable a script reads, or to run the command yourself. A saved allow rule does not clear the refusal, and neither does the auto-mode classifier.
The mod's wider net, beyond shell commands
The 2.1.321 narrowing is about shell commands. The README describes the same mod watching other surfaces with the same address-plus-word test:
- File writes. Write, Edit and NotebookEdit calls are refused when what is being written meets the test. An Edit is refused only when the new text meets the test and the replaced text does not, since carrying over a line a file already holds adds nothing.
- Web addresses. Your address inside a URL is refused with no second word needed, because the URL itself is what goes out.
- MCP tools. The whole input of an MCP tool call, keys included, is tested the same way.
- Scripts a command names. For shell calls, the text of each script the command names is tested as well as the command line itself, which closes the route of writing the address into a script and running that instead.
What it never claimed to be
The README's own sentence is the honest summary: this is a courtesy against a well-meaning model, not a boundary. Its list of what passes is long. Your address with no caller word beside it passes — in a request body, in a curl -u argument, in an MCP field such as a calendar invite, or in a file such as package metadata. Values a script reads while it runs pass, because the test sees only the text it is given. An address read on one line and a User-Agent set on another passes. Some tools are outside the test altogether: the address inside a Web search prompt is not covered, and neither are the browser tools or the local read tools. The matching itself is two word searches over the text, with no parser, so it also refuses some harmless calls — the README accepts those false refusals as the price of a simple test.
What to do
- If scheduled runs or ordinary commands stopped at the email prompt, update to 2.1.321 or later: only the address-plus-User-Agent combination is refused now.
- If you turned the mod off because of those stops, the setting is worth revisiting: it is disabled through the plugin settings, and a repository's own settings cannot turn it off.
- If your concern is the address leaving the machine at all, do not treat the mod as the control for that. Its README lists the paths it does not cover; the boundary has to come from what the model is given and from your permission rules, not from this test.
Related playbooks
- Check citations against the reference list
- Turn meeting notes into action items and a follow-up email
- Schwab lets Claude into your brokerage account
- Simon Willison's mystery beep, triangulated
Sources
- Claude Code v2.1.321 release notes — anthropics/claude-code, GitHub
- privacy mod README — anthropics/claude-code, GitHub
Back to: Everyday tasks playbooks hub · Also: Claude Code sent your email to websites