CVE-2025-32018 | Arbitrary file write from Cursor Agent through a prompt injection from malicious @Docs

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.

Published: 2025-04-08 Last update: 2026-04-15 Assigner: [email protected] Source: [email protected]
NVD Status：Deferred，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2025-32018 is rated Moderate Risk (49.3/100): CVSS High severity, with low exploitation likelihood (EPSS 0.26%). Review affected assets and schedule remediation.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2025-32018

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-05-19 0.22% 0.26% +0.04%
2 2026-02-02 0.06% 0.22% +0.15%
3 2025-12-23 — 0.06% —

Full EPSS history (8 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2025-32018

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
8.0 3.1 HIGH
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:H)
Even with access, the exploit needs extra luck, timing, or a fussy environment to actually work.
Privileges required (PR:L)
A normal user session is enough; they don’t have to be admin.
User interaction (UI:R)
A real person has to do something—click, install, enable—otherwise it doesn’t land.
Scope (S:C)
Breaking this can reach past the original component and bite other resources—bigger blast radius.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 1.3 6.0 [email protected]

Weakness enumeration for CVE-2025-32018

Affected software / configurations for CVE-2025-32018

Vendor Product Version Raw CPE
No affected products in dataset.

References for CVE-2025-32018

cvelogic Threat Intelligence