NVD / CVE Program· CNA GitHub_M

CVE-2025-64106: Cursor: Speedbump Modal Bypass in MCP Server Deep-Link

HighCVSS 8.8 · v3.1—No exploit No fix recorded

Noroxi assessment

Priority: Monitor (action score 35/100)

The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
Probability of exploitation in the next 30 days: 0.43% (FIRST EPSS).
Anyone who can reach it over the internet can trigger it. No account or password is required. A user must open a link or visit a page. No special conditions are required; it is repeatable.
According to the record, no fixed version is available yet.

Low priority for now. Update when a fix is released; follow the vendor's advisory.

Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it

Primary sources: NVD · CVE.org · FIRST EPSS

Cursor is a code editor built for programming with AI. In versions 1.7.28 and below, an input validation flaw in Cursor's MCP server installation enables specially crafted deep-links to bypass the standard security warnings and conceal executed commands from users if they choose to accept the server. If an attacker is able to convince a victim to navigate to a malicious deeplink, the victim will not see the correct speedbump modal, and if they choose to accept, will execute commands specified by the attackers deeplink.

Published: Nov 4, 2025
Updated: Oct 19, 2026
EPSS: 0.4% · 37th percentile
CWE: CWE-78

Report tools

JSON

Action score

Monitor

Low priority for now.

CVSS: 35 / 40 · 8.8 / 10
CISA KEV: 0 / 30 · Not listed
EPSS: 0 / 30 · 0.4%

CISA SSVC decision

Exploitation: none
Automatable: no
Technical impact: total

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD: —
CNA · GitHub_M: 8.8; NVD has not scored this yet; the score shown is the CNA’s.

The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.

Get told when this record changes

Not in KEV: no record of exploitation in the wild
No public exploit code on record
No fixed version yet

If any of these changes, we'll tell you in the daily email digest.

Is your version affected? Check it

Noroxi analysis

What does it mean in your environment?

The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.

We use this product, ask for help

Affected systems

Is your version affected?

Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.

Vendor	Product	CPE
anysphere	cursor	cpe:2.3:a:anysphere:cursor

Affected versions

NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.

anysphere cursorbefore 2.0

Versions reported by the vendor

Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.

cursor cursor
- < 2.0affected

Same product

anysphere: all records

Other highest-scoring records for the same primary product.

CVE-2025-54136Cursor's Modification of MCP Server Definitions Bypasses Manual Re-approvals
44Plan
CVE-2025-54135Cursor Agent is vulnerable to prompt injection via MCP Special Files
40Plan
CVE-2026-26268Cursor sandbox escape via Git hooks
39Monitor

Published before and after this one in the same product

← EarlierCVE-2025-61593Oct 3, 2025 · Cursor CLI Agent: Sensitive File Overwrite Bypass
35Monitor
← EarlierCVE-2025-59944Oct 3, 2025 · Cursor IDE: Sensitive File Overwrite Bypass is Possible
39Monitor
Later →CVE-2025-64107Nov 4, 2025 · Cursor is Vulnerable to Path Manipulation Using Backslashes on Windows
35Monitor

Remediation

Which version to upgrade to

Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.

No fix version is recorded for this entry. Check the references for vendor advisories.

Exploit status

No known public exploit

No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.

Research context

For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.

Timeline

From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.

No dated events beyond publication.

No history yet (it accumulates with the daily EPSS job).

Patch and commit links

Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.

No commit or PR link among the references.

Credits

All researchers

Finders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.

No credits in the CNA record.

Variant candidates

Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.

CVE-2025-5413695 days apartCursor's Modification of MCP Server Definitions Bypasses Manual Re-approvals
44Plan
CVE-2025-5413592 days apartCursor Agent is vulnerable to prompt injection via MCP Special Files
40Plan
CVE-2025-6159132 days apartCursor CLI's Cursor Agent MCP OAuth2 Communication is Vulnerable to Remote Code Execution
35Monitor
CVE-2026-31854127 days apartCursor Affected by Arbitrary Code Execution via Prompt Injection and Whitelist Bypass
34Monitor
CVE-2025-5413395 days apartCursor's MCP Install Deeplink Does Not Show Arguments in its User-Dialog
21Monitor

Chain candidates

An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.

—

Bug bounty scope

No known public program.

Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).

Technical details

Attack conditions

Anyone who can reach it over the internet can trigger it.
No account or password is required.
A user must open a link or visit a page.
No special conditions are required; it is repeatable.

If successful

Confidentiality: high · data can be read
Integrity: high · data or configuration can be modified
Availability: high · the service can be disrupted

Attack vector: Network
Attack complexity: Low
Privileges required: None
User interaction: Required
Scope: Unchanged
Confidentiality impact: High
Integrity impact: High
Availability impact: High

Weakness class (CWE)

CWE-78 · Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

CVSS vector

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

nvd-secondary

Root cause

User input is inserted as text into a shell command. The shell may interpret special characters in the input as part of the command.

The bug in code

The whole CWE-78 class

A representative example of this vulnerability class. Not the vendor's source code; it shows the faulty pattern and its fix.

Vulnerable

1const host = req.body.host;
2exec("ping -c 1 " + host, onResult);

Fixed

1const host = req.body.host;
2if (!/^[a-z0-9.-]{1,253}$/i.test(host)) return res.sendStatus(400);
3execFile("ping", ["-c", "1", host], onResult);

Attack context

MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.

Attack patterns (CAPEC)

ATT&CK techniques

—

Change log

No changes recorded on tracked fields yet. Score, KEV, exploit maturity and fix status changes appear here.

References

github.com/cursor/cursor/security/advisories/GHSA-4575-fh42-7848

Vendor advisories and official records. Exploit/PoC links are deliberately left out.

All records