---
title: Claude Code put signed-in account emails into User-Agent on web/shell calls; 2.1.317 adds a default privacy mod with known gaps | ctxsec
url: https://ctxsec.com/items/claude-code-user-agent-email-privacy-mod-2-1-317
description: "Users reported Claude Code sending their Anthropic account email in HTTP User-Agent headers when the agent contacted third-party sites (Wikipedia, SEC EDGAR and others that ask scrapers for a contact). Anthropic had placed the address in model context to reduce author-name hallucinations; the model volunteered it. Version 2.1.317+ ships cc-plugin-privacy (on by default): a tool.check hook that refuses Bash/PowerShell/Monitor calls whose input both contains that address and names a User-Agent. Anthropic staff say a fuller fix is to stop putting the email in context. The mod README lists gaps: WebFetch/WebSearch/MCP unchecked, URLs/bodies/From headers, runtime-computed emails, scripts, and other clients."
status: "confirmed (GitHub issue #107757 Nov 5; Anthropic cc-plugin-privacy README / 2.1.317+); Anthropic says fuller removal of email from context planned; mod is a courtesy not a hard boundary"
published: 2026-11-05
---

> Users reported Claude Code sending their Anthropic account email in HTTP User-Agent headers when the agent contacted third-party sites (Wikipedia, SEC EDGAR and others that ask scrapers for a contact). Anthropic had placed the address in model context to reduce author-name hallucinations; the model volunteered it. Version 2.1.317+ ships cc-plugin-privacy (on by default): a tool.check hook that refuses Bash/PowerShell/Monitor calls whose input both contains that address and names a User-Agent. Anthropic staff say a fuller fix is to stop putting the email in context. The mod README lists gaps: WebFetch/WebSearch/MCP unchecked, URLs/bodies/From headers, runtime-computed emails, scripts, and other clients.

[← Context & Harness Attacks](/context) · [markdown](/items/claude-code-user-agent-email-privacy-mod-2-1-317.md)

confirmed (GitHub issue #107757 Nov 5; Anthropic cc-plugin-privacy README / 2.1.317+); Anthropic says fuller removal of email from context planned; mod is a courtesy not a hard boundary

2026-11-05

### Claude Code put signed-in account emails into User-Agent on web/shell calls; 2.1.317 adds a default privacy mod with known gaps

- **Do now:** update Claude Code to 2.1.317 or later; leave `cc-plugin-privacy` enabled (it can be disabled via `/plugin` or `enabledPlugins`).
- **Harness lesson:** anything in an agent's context can leave on a tool call. Prefer egress allowlists and strip identity from prompts unless a named site needs a contact.
- Reporter in #107757 linked the leak to floods of scam email and said they were migrating off Claude Code.

Sources: [GitHub: anthropics/claude-code#107757 — Privacy violation in User-Agent header](https://github.com/anthropics/claude-code/issues/107757) · [Anthropic Claude Code: mods/privacy README (cc-plugin-privacy)](https://raw.githubusercontent.com/anthropics/claude-code/main/mods/privacy/README.md)