CVE-2025-64110: Cursor logic bug lets agent read files protected by cursorignore

Summary

CVE-2025-64110 affects Cursor, a code editor built for programming with AI, in versions 1.7.23 and below. A logic bug lets a malicious agent 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 that invalidates the configuration of pre-existing ones.

Mitigation

This issue is fixed in version 2.0.

Related items

• InfoTop agent skill security resources — November 2026Similar attack · Adversa AI Blog
• InfoHow to Turn AI Red Team Findings Into Runtime ControlsSimilar attack · Straiker Blog
• MediumDocker Sandboxes vulnerability lets AI agents access sensitive files outside their sandbox (CVE-2026-103916) | Endor LabsSimilar attack · Endor Labs Blog
• MediumFree the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak BundlesSimilar attack · Check Point Research
• InfoRight Tool, Wrong Parameters: Defending LLM Agents Against Parameter PoisoningSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)