CVE-2025-54135 Cursor Agent is vulnerable to prompt injection via MCP Special Files

High 8.6 Published Updated

Attackers can achieve remote code execution by exploiting prompt injection to write malicious MCP configuration files without user approval.

Exploited in the wild
Not known
Login needed
Any signed-in user
Attackable
Over the internet
Victim action needed
Not needed
Fix
None listed

What is CVE-2025-54135?

CVE-2025-54135 is a high-severity code injection vulnerability in cursor, published on 5 Aug 2025. Any signed-in user can exploit it over the network, with no action from the victim.

Official description

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions below 1.3.9, If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive MCP files, such as the .cursor/mcp.json file don't already exist in the workspace, an attacker can chain a indirect prompt injection vulnerability to hijack the context to write to the settings file and trigger RCE on the victim without user approval. This is fixed in version 1.3.9.

Weakness: CWE-829, CWE-78

Which versions are affected by CVE-2025-54135?

It affects 1 product.

Products include Anysphere Cursor.

How do I fix CVE-2025-54135?

No fix has been published for CVE-2025-54135 yet. Limit exposure of the affected software until one is available.

Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.

Is CVE-2025-54135 being exploited?

There is no known exploitation of CVE-2025-54135 in the wild and no public exploit code.

Public exploit code: 2 proofs of concept on GitHub.

Sources

Is CVE-2025-54135 in your software?

Upload an SBOM and sbomify checks it against every vulnerability here, every day.

Check your SBOMs for free