vibehacker
News
Fathom ·

Claude Code has been putting users' emails into web request User-Agent headers

Fathom reports Claude Code injects the signed-in account email into model instructions, and users caught it appearing in User-Agent headers on requests to sites like the SEC, Wikipedia, and crates.io—mostly via sub-agents. Anthropic added a permission check in 2.1.317 (Nov 2) that asks before web or shell calls send that address to the network.

More news

View all

Qwen Code 0.26.9 adds Skill ZIP installs and bulk Skill activation

Released Nov 6, Qwen Code 0.26.9 lets you install large Skill ZIPs via the daemon API, TypeScript SDK, or Web Shell, and toggle 1–100 Skills in one PUT /skills/activation call. It also turns managed agent automation on by default, adds image input for Llama 4, Pixtral, and Mistral Small models, and reports working/blocked/done status to terminals via OSC 7501…

Apiiro: Claude Code "don't ask again" left secrets in 1,122 public GitHub copies

Apiiro found 1,122 public .claude/settings.local.json copies holding at least one secret (1,379 distinct, including 379 database passwords) after "Yes, and don't ask again" saves the full approved command—credentials included—in plain text. Claude Code only adds the file to the user's global git excludes, not the project's .gitignore , so already committed copies and forks stay exposed; rotate first, then clean up…

The Hacker News

Spotted something we missed? Start a thread.