CVE-2026-22708
Cursor has a Terminal Tool Allowlist Bypass via Environment Variables
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.
INFO
Published Date :
Jan. 14, 2026, 5:16 p.m.
Last Modified :
Feb. 3, 2026, 6:36 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | CRITICAL | [email protected] | ||||
| CVSS 4.0 | HIGH | [email protected] |
Solution
- Update Cursor to version 2.3 or later.
- Disable Auto-Run Mode if not actively needed.
- Review and restrict environment variable modifications.
Public PoC/Exploit Available at Github
CVE-2026-22708 has a 6 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-22708.
| URL | Resource |
|---|---|
| https://github.com/cursor/cursor/security/advisories/GHSA-82wg-qcm4-fp2w | Vendor Advisory |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-22708 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-22708
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
8-Layer Security Blueprint for Autonomous AI Agents. Defense-in-depth for OpenClaw, LangChain, CrewAI, AutoGPT, and any AI agent on Linux.
agentic-ai ai-agents ai-security canary-tokens defense-in-depth linux-security nftables openclaw-security owasp soar
Shell
Security-first AI agent for WhatsApp. Built as an answer to OpenClaw's architecture.
ai-agent llm openclaw prompt-injection python security typescript whatsapp
Dockerfile Python TypeScript Shell HTML
Security guardrails for AI coding agents. Blocks prompt injection, prevents credential exfiltration, scans session logs.
api-key-scanner cloudflare-workers github-scanner indie-dev prompt-injection security typescript vibe-coding
TypeScript JavaScript
enabling the safe use of OpenClaw
TypeScript CSS JavaScript
Proactive security monitoring for OpenClaw deployments. Detects ClawHavoc, AMOS stealer, CVE-2026-25253, memory poisoning, and supply chain attacks.
HTML JavaScript Shell
Autonomous Cybersecurity Operations and Red Teaming Agent
aisoc soc ai-agents ai-red-team readteaming redteam-tools security-red-team soc-agent security-agent security-tools
JavaScript TypeScript
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-22708 vulnerability anywhere in the article.
-
The Hacker News
Google Gemini Prompt Injection Flaw Exposed Private Calendar Data via Malicious Invites
Cybersecurity researchers have disclosed details of a security flaw that leverages indirect prompt injection targeting Google Gemini as a way to bypass authorization guardrails and use Google Calendar ... Read more
The following table lists the changes that have been made to the
CVE-2026-22708 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
Initial Analysis by [email protected]
Feb. 03, 2026
Action Type Old Value New Value Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Added CWE CWE-77 Added CPE Configuration OR *cpe:2.3:a:anysphere:cursor:*:*:*:*:*:*:*:* versions up to (excluding) 2.3 Added Reference Type GitHub, Inc.: https://github.com/cursor/cursor/security/advisories/GHSA-82wg-qcm4-fp2w Types: Vendor Advisory -
New CVE Received by [email protected]
Jan. 14, 2026
Action Type Old Value New Value Added 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. Added CVSS V4.0 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 Added CWE CWE-94 Added CWE CWE-78 Added CWE CWE-77 Added CWE CWE-74 Added CWE CWE-15 Added CWE CWE-269 Added Reference https://github.com/cursor/cursor/security/advisories/GHSA-82wg-qcm4-fp2w