What is the CVSS score of CVE-2026-22708?

CVE-2026-22708 has a CVSS 3.1 base score of 9.8 (Critical). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H. EPSS exploitation probability: 0.1%.

Is there a public PoC exploit available for CVE-2026-22708?

Yes, a public proof-of-concept exploit is available for CVE-2026-22708. Prioritise patching immediately. EPSS: 0.1%.

How to fix or mitigate CVE-2026-22708?

Within 24 hours: Identify all affected systems and apply vendor patches immediately. Monitor vendor channels for patch availability.

Cursor CVE-2026-22708

CRITICAL

External Control of System or Configuration Setting (CWE-15)

2026-01-14 security-advisories@github.com

Code Injection AI / ML Cursor Anysphere

9.8

CVSS 3.1 · GitHub Advisory

View

Attack ChainAIDerived

Hypothetical attack flow derived from CVE metadata – not a confirmed exploit chain

Access

Inject malicious prompt into Cursor Agent
Delivery

Trigger shell built-in execution
Exploit

Bypass allowlist restrictions
Execution

Modify environment variables
Impact

Poison trusted command execution

Vulnerability Assessment

Weakness	CWE CWE-15 OWASP Top 10:2025 A02:2025 - Security Misconfiguration ASVS 5.0 V13 - Configuration Configuration hardening
Exploitation Conditions	Cursor Agent must be running in Auto-Run Mode with Allowlist mode enabled. Attacker requires ability to provide input prompts (direct or indirect injection) to the Agent. No authentication required for prompt injection.
Impact	CVSS 9.8 (Critical). No auth (prompt injection via code or chat). AI code editors have broad filesystem and command access. EPSS 0.06%.
Exploit ScenarioDerived	A malicious codebase contains a comment with instructions that trick Cursor's AI agent into setting PATH to include an attacker-controlled directory, then running what appears to be a safe command that actually executes the attacker's binary.

Act Now Prioritize within 24-48h. Why: CRITICAL severity + public POC available.

No patch listed yet 0.1% exploitation probability (EPSS)

Get an e-mail when this CVE is exploited, patched or re-scored. Free account.

Alert me

AnalysisAIv1 – Mar 12, 2026

Cursor AI code editor before 2.3 allows prompt injection to bypass the Agent's Allowlist mode. Shell built-ins can execute without appearing in the allowlist, enabling environment poisoning and arbitrary command execution.

Earlier versions of this analysis (1)

v1 Mar 12, 2026 - 21:54 CVSS 9.8

Cursor AI editor allows shell built-in execution bypassing the Agent Allowlist, enabling environment poisoning via prompt injection.

RemediationAI

Update to Cursor 2.3 or later. Review AI agent execution logs for suspicious shell built-in usage.

Affects your stack

Find out whether the stacks and servers you run are on an affected version.

Checking this CVE against your own stacks and servers is part of the Basic plan and up.

Technical ContextAI · show details

The Agent's Auto-Run Mode with Allowlist only checks explicit commands, not shell built-ins like export, alias, and set (CWE-15). Through prompt injection, an attacker can manipulate environment variables, redefine commands via aliases, and poison the shell environment.

Know when Cursor gets its next vulnerability

Watch products and get an email when something new is published
Check this CVE against your own stack and servers
Exploit and PoC references, threat intelligence from 22 sources

Continue with Google Continue with GitHub

No credit card · 7-day full trial

Severity by source

GitHub Advisory PRIMARY 9.8 CRITICAL

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

Primary rating from GitHub Advisory · only source for this CVE.

CVSS VectorGitHub Advisory

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

DescriptionGitHub Advisory

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.

Executive ViewAI

Why It Matters

Organizations using Cursor face critical risk from CVE-2026-22708 rated CVSS 9.8. Successful exploitation could critically impact the confidentiality, integrity, and availability of affected systems. Organizations should apply vendor updates immediately when available and implement compensating controls in the interim.

Business Impact: Severe

Compensating Controls

Apply vendor patch. If immediate patching is not feasible: (1) Implement network-level access controls to limit exposure; (2) Enable enhanced monitoring and alerting; (3) Apply principle of least privilege.

Threat Intelligence Overview

EPSS Score

0.1%

Top 80% exploitable

Exploit

POC

Public exploit code exists

Data Quality

4 sources

Confidence: Medium

NVD

CVE.org

EPSS

GitHub

How this decision was reached

The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.

SignalValue

Severity CRITICAL

CISA KEV No

Public POC Yes

EPSS 0.1%

Patch available No

Active threat No

Deciding rule

CRITICAL severity + public POC available

What every action level means

Emergency Immediate action required. Criteria: CRITICAL + in CISA KEV (actively exploited) without patch, OR CRITICAL + EPSS > 30% without patch, OR CRITICAL + active threat signals without patch.

Act Now Prioritize within 24-48h. Criteria: in KEV with patch available, OR CRITICAL + public POC, OR HIGH + EPSS > 10%, OR CRITICAL + active threat, OR any CRITICAL severity.

This Week Schedule remediation this week. Criteria: HIGH severity (CVSS 7.0-8.9). Patch within normal change window.

This Month Plan within 30 days. Criteria: MEDIUM severity (CVSS 4.0-6.9), lower exploitation probability. Include in regular patch cycle.

Monitor Track and reassess. Criteria: LOW severity (CVSS 0.1-3.9), minimal exploitation risk. No immediate action needed.

SSVC AssessmentENISA

SSVC Decision· derived

Out-of-Cycle

Exploitation· derived

Poc

System Exposure· derived

Open

Automatable· derived

Yes

Human Impact

Very High

Priority Score

Low Medium High Critical

KEV: 0

EPSS: 0

CVSS: +49

PoC: +20

Weaponized: 0

Threat intel: 0

Gov advisory: 0

Attack Technique

Code Injection CRITICAL

Code injection occurs when an application accepts user input and passes it directly into a language interpreter or evaluator without proper sanitization.