Vulnerability · Published Apr 8, 2025 · Assigned by GitHub_M
CVE-2025-32018Arbitrary file write from Cursor Agent through a prompt injection from malicious @Docs
High 8.1
In plain English
A high-severity path traversal in cursor from getcursor. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 36% of all known vulnerabilities).
Official description
Cursor is a code editor built for programming with AI. In versions 0.45.0 through 0.48.6, the Cursor app introduced a regression affecting the set of file paths the Cursor Agent is permitted to modify automatically. Under specific conditions, the agent could be prompted, either directly by the user or via maliciously crafted context, to automatically write to files outside of the opened workspace. This behavior required deliberate prompting, making successful exploitation highly impractical in real-world scenarios. Furthermore, the edited file was still displayed in the UI as usual for user review, making it unlikely for the edit to go unnoticed by the user. This vulnerability is fixed in 0.48.7.
Affected products (as reported)
Weakness: CWE-22 · Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:H
References
- https://github.com/getcursor/cursor/security/advisories/GHSA-qjh8-mh96-fc86 x_refsource_CONFIRM