Code execution via unauthorized MCP configuration creation
Published Aug 5, 2025 · Updated Aug 5, 2025
Prompt injection in Cursor before 1.3.9 allows attackers to execute arbitrary code through an unauthorized MCP configuration. Agent permits creation of a new dotfile without approval, so injected instructions can create .cursor/mcp.json and register attacker-chosen MCP commands. The chain requires that sensitive file to be absent and malicious instructions to enter Agent context; registered commands then run without approval.
Summary
What happened
Prompt injection in Cursor before 1.3.9 allows attackers to execute arbitrary code through an unauthorized MCP configuration. Agent permits creation of a new dotfile without approval, so injected instructions can create .cursor/mcp.json and register attacker-chosen MCP commands. The chain requires that sensitive file to be absent and malicious instructions to enter Agent context; registered commands then run without approval.
The record
- CVE
- CVE-2025-54135
- Published
- Aug 5, 2025
- Updated
- Aug 5, 2025
- Vendor
- Anysphere
- Product
- Cursor
- Classifications
- CWE-829, CWE-78, T1059
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Aug 5, 2025CVE publishedPublication date reported by the CVE source.
- Aug 5, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 1.3.9
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo