Cyber Resilience

CVE-2025-49150

Medium

Published: 11 June 2025

Published
11 June 2025
Modified
15 April 2026
KEV Added
Patch
CVSS Score v3.1 5.9 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N
EPSS Score 0.0020 41.5th percentile
Risk Priority 12 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2025-49150 is a medium-severity Exposure of Sensitive Information to an Unauthorized Actor (CWE-200) vulnerability. Its CVSS base score is 5.9 (Medium).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exfiltration Over C2 Channel (T1041); ranked at the 41.5th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as Enterprise AI Assistants; in the LLM/Generative AI Risks risk domain; MITRE ATLAS techniques in scope: LLM Prompt Injection (AML.T0051).

EU & UK References

Vulnerability details

Cursor is a code editor built for programming with AI. Prior to 0.51.0, by default, the setting json.schemaDownload.enable was set to True. This means that by writing a JSON file, an attacker can trigger an arbitrary HTTP GET request that…

more

does not require user confirmation. Since the Cursor Agent can edit JSON files, this means a malicious agent, for example, after a prompt injection attack already succeeded, could trigger a GET request to an attacker controlled URL, potentially exfiltrating other data the agent may have access to. This vulnerability is fixed in 0.51.0.

CWE(s)

AI Security AnalysisAI

AI Category
Enterprise AI Assistants
Risk Domain
LLM/Generative AI Risks
OWASP Top 10 for LLMs 2025
LLM01:2025 Prompt Injection
Classification Reason
Matched keywords: ai, prompt injection

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

T1041 Exfiltration Over C2 Channel Exfiltration
Adversaries may steal data by exfiltrating it over an existing command and control channel.
Why these techniques?

The vulnerability allows a compromised Cursor Agent to craft JSON files that trigger arbitrary HTTP GET requests to attacker-controlled URLs, enabling data exfiltration over a C2 channel by embedding sensitive data in the request.

MITRE ATLAS TechniquesAI

MITRE ATLAS techniques

AML.T0051: LLM Prompt Injection

Affected Assets

Mitigating Controls

Likely Mitigating Controls AI

Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.

addresses: CWE-200

Automated marking applies security attributes to system outputs, making it harder for attackers to exploit unmarked sensitive information leading to unauthorized exposure.

addresses: CWE-200

Proper attribute retention and permitted-value enforcement limits unauthorized actors from accessing sensitive information lacking correct labels.

addresses: CWE-200

Prevents unauthorized exposure of sensitive information by prohibiting untrusted external systems from processing or storing it.

addresses: CWE-200

By enforcing authorization matching prior to sharing, the control reduces the risk of exposing sensitive information to unauthorized actors.

addresses: CWE-200

Review and removal of nonpublic information from publicly accessible systems directly prevents exposure of sensitive data to unauthorized actors.

addresses: CWE-200

Data mining protection mechanisms detect and block unauthorized bulk extraction of sensitive data, directly mitigating exposure to unauthorized actors.

addresses: CWE-200

Literacy training teaches users to recognize and avoid actions that result in unauthorized exposure of sensitive information.

addresses: CWE-200

Retaining and monitoring training records confirms personnel have completed privacy and security awareness training on handling sensitive data, reducing the chance of unauthorized exposure due to lack of knowledge.

References