Cursorignore Bypass via New Cursorignore Write

Summary

A logic bug in Cursor allows a malicious agent to read sensitive files that should be protected via cursorignore. An attacker who has already achieved prompt injection, or a malicious model, could create a new cursorignore file which can invalidate the configuration of pre-existing ones. This could allow a malicious agent to read protected files.

Impact

When chained with a successful prompt injection or malicious model, this bug allows the agent to bypass cursorignore protections and read protected files. If a user has non-default auto-run settings or is tricked via social engineering, this data could be exfiltrated from the machine.

Remediation

The agents ability to create and edit cursorignore files has been blocked in all cases.