Skip to content
Fencer Intel
high 8.1

CVE-2025-32018 json

Arbitrary file write from Cursor Agent through a prompt injection from malicious @Docs

published last yr. modified 4mo ago also EUVD-2025-10400

cvss
8.1
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.4%
EPSS 0.4% chance of exploitation in 30 days, percentile 36%
public exploits
0
none known

Summary

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.

Is CVE-2025-32018 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
total
Assessed
last yr.

Exploit prediction

0.42% chance of exploitation in the next 30 days, higher than 36% of all scored CVEs (FIRST EPSS, 2026-11-09).

CVSS scores

assigned by version score vector
CNA 3.1 8.1 CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:H

Affected products

  • getcursor cursor

Classification

Weakness
  • CWE-22 Improper Limitation of a Pathname to a Restricted Directory

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.