Critical severity9.8NVD Advisory· Published Jan 14, 2026· Updated Jun 17, 2026

CVE-2026-22708

Description

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via indirect or direct prompt injection to poison the shell environment by setting, modifying, or removing environment variables that influence trusted commands. This vulnerability is fixed in 2.3.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected products

Anysphere/Cursor
cpe:2.3:a:anysphere:cursor:*:*:*:*:*:*:*:*
Range: <2.3
Getcursor/Cursor Agentllm-create
Range: <2.3
Getcursor/Cursorllm-create2 versions
<2.3+ 1 more
- (no CPE)range: <2.3
- (no CPE)range: < 2.3

Patches

Vulnerability mechanics

References

github.com/cursor/cursor/security/advisories/GHSA-82wg-qcm4-fp2wnvdVendor Advisory

News mentions

Prompt injection still drives most agentic AI security failures in production
Help Net Security · Jun 11, 2026
Google Fixes Critical RCE Flaw in AI-Based 'Antigravity' Tool
Dark Reading · Apr 21, 2026

Severity

CriticalCVSS v3.1

9.8/ 10

CVSS v47.2

CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:U/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Attack vector: Network
Complexity: Low
Privileges: None
User interaction: None
Scope: Unchanged
Confidentiality: High
Integrity: High
Availability: High

Vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

EPSS

Probability of exploitation in the next 30 days.

0.56%

VYPR risk score

Composite of severity, exploitation, and reach.

0.64high

cvss	0.637
epss	0.000
exploit	0.000
kev	0.000
patch	0.000
ransomware	0.000

Weaknesses

CWE-15
External Control of System or Configuration Setting
CWE-269
Improper Privilege Management
CWE-74
Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')
CWE-77
Improper Neutralization of Special Elements used in a Command ('Command Injection')
CWE-78
Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
CWE-94
Improper Control of Generation of Code ('Code Injection')

CVE ID

CVE-2026-22708