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.
0.8%(unchanged from 0.8% a week ago; 0.8% 30 days ago) estimated probability of exploitation activity in the next 30 days; 58th percentile. Scored 2026-11-21. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: no · Technical impact: total, assessed 2026-01-14. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWEs
CWE-77Improper Neutralization of Special Elements used in a Command CWE-15External Control of System or Configuration Setting CWE-74Improper Neutralization of Special Elements in Output Used by a Downstream Component (Injection) CWE-78Improper Neutralization of Special Elements used in an OS Command (OS Command Injection) CWE-94Improper Control of Generation of Code (Code Injection) CWE-269Improper Privilege Management
Show the promptExplain CVE-2026-22708 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-22708?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-22708?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-22708 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.
Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.
CAPEC-6 Argument Injection Likelihood: High · Severity: High
CAPEC-15 Command Delimiters Likelihood: High · Severity: High
CAPEC-43 Exploiting Multiple Input Interpretation Layers Likelihood: Medium · Severity: High
CAPEC-88 OS Command Injection Likelihood: High · Severity: High
The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits. More on the page of CWE-78, CWE-77, CWE-15, CWE-74 (37).