MediumVulnerabilityLLM-specific

CVE-2025-54131: Cursor allow list bypass in auto-run mode via backtick or command substitution

Source: NVD(opens in a new tab)
Identifier: CVE-2025-54131
Published: August 1, 2025
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.5%

Summary

CVE-2025-54131 affects Cursor, a code editor built for programming with AI, in versions below 1.3. When a user has switched from the default approval-for-every-terminal-call setting to an allowlist, an attacker can bypass the allow list in auto-run mode using a backtick (`) or $(cmd) and execute arbitrary commands without user approval. The flaw can be triggered when chained with indirect prompt injection.

Mitigation

This is fixed in version 1.3.

Details

Scores and exploitation

CVSS score: 6.4(medium)
EPSS: 0.5%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-77
Attack pattern (CAPEC): CAPEC-88
AI threat technique (MITRE ATLAS): AML.T0051
AML.T0054

Classification

Attack type: Jailbreak,
Prompt injection
Attack sophistication: Moderate
AI component targeted: Agent
Impact: Confidentiality,
Integrity
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2025-54131

First tracked: February 15, 2026 at 08:52 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Topics

Prompt injection and jailbreaks

Summary

Mitigation

Topics

Related items