{"id":184165,"date":"2026-11-06T11:41:02","date_gmt":"2026-11-06T09:41:02","guid":{"rendered":"https:\/\/prohoster.info\/blog\/news\/claude-code-raskryval-email-polzovatelya-pri-obrashhenii-k-nekotorym-sajtam"},"modified":"2026-11-06T11:41:08","modified_gmt":"2026-11-06T09:41:08","slug":"claude-code-exposed-user-email-addresses-when-accessing-certain-websites","status":"publish","type":"post","link":"https:\/\/prohoster.info\/en\/blog\/news\/claude-code-exposed-user-email-addresses-when-accessing-certain-websites","title":{"rendered":"Claude Code revealed the user's email when accessing certain websites.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"
A privacy issue was identified in the AI agent Claude Code, which caused email address leaks when accessing certain third-party websites. The email was disclosed in the User-Agent HTTP header without user consent and without the option to disable this behavior. The substitution occurred for certain sites like Wikipedia and the SEC (Securities and Exchange Commission), which do not accept requests from bots that do not include the owner's email. According to a comment from a representative of Anthropic, this activity was not an intentionally added feature, but rather an independent action by the AI model that considered the requirements for bot request formatting and the recommendations of RFC-9110, which dictate that a contact email must be provided for automated requests.<\/p>\n
Information about the email associated with the user's account in Claude Code was transmitted to the AI model so that it could consider the context when processing tasks related to the user and their account. Without such context, the model would hallucinate and use fabricated information, for example, in the tags \"@author\". As a side effect, the AI model began using the email not only for intended purposes but also while performing ancillary tasks, such as inserting it into the User-Agent field when generating launch strings for the curl utility. <\/p>\n
To block the leakage of email in external requests \nthe cc-plugin-privacy plugin has been prepared, which is included in the standard set of plugins and activated by default in the release of claude-code 2.1.317. The plugin asks the user for confirmation before applying web tools or generating curl-style commands that mention the email. The plugin does not solve all possible leakage paths; for instance, it does not help in situations where Claude generates and executes a script on its own. \nTo completely block the problem in the next release of Claude Code, which is planned to be released in a few days, it has been decided to remove the email from the context sent to the AI model. \n Source: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"