Apr 2, 2026Confirmed
Claude Code reportedly hid Unicode markers in prompts to flag custom API endpoints; Anthropic removed them
Rogue: Hid what it didWhat is hidden from viewData exfiltrationDERIVED
Approved by person, Oct 11, 2026. How entries are approved
Researchers found Anthropic's Claude Code classified custom API endpoint hostnames and two system timezones. It encoded the results in system prompts using look-alike Unicode apostrophes and altered date separators. Anthropic called it an anti-reseller and anti-distillation experiment begun in March, and removed it after the disclosure.
What this means for youA tool you run may quietly collect details about your setup and send them along without telling you. If you use AI coding tools with custom or third-party connections, check the vendor's documentation and privacy terms for what they collect.
Sources
- AI Incident Databasehttps://incidentdatabase.ai/cite/1723
Data from the AI Incident Database (incidentdatabase.ai), licensed CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/). McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. IAAI-21.
Source data license: CC BY-SA 4.0 (database). Report contents keep their own rights; reports.text, submissions, images and videos are excluded from the data license.
rogue:R2
Covered by snapshot 45
da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a
This entry is record number 2237. It has not been edited since it was approved; the hash above would not match if it had. How to verify