CVE-2025-61593

Affects: prompt injection

CVSS: HIGH · 7.1v3.1
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H
Published: 2025-10-03
Weakness: CWE-94, CWE-178
Source: nvd.nist.gov/vuln/detail/CVE-2025-61593

Description

Cursor is a code editor built for programming with AI. In versions 1.7 and below, a vulnerability in the way Cursor CLI Agent protects its sensitive files (i.e. */.cursor/cli.json) allows attackers to modify the content of the files through prompt injection, thus achieving remote code execution. A prompt injection can lead to full RCE through modifying sensitive files on case-insensitive filesystems. This issue is fixed in a commit, 25b418f, but has yet to be released as of October 3, 2025.

References

https://github.com/cursor/cursor/security/advisories/GHSA-x2vq-h6v6-jhc6

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2025-61593 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming