Lucene search
K

8 matches found

Positive Technologies
Positive Technologies
added 2026/06/10 12:0 a.m.10 views

PT-2026-48540

Due to the combination of checking out PR head branches attacker-controlled, reading .mcp.json from the working directory via default setting sources, and unconditionally enabling all project MCP servers via enableAllProjectMcpServers, it was possible for an attacker who opened a PR containing a...

5.3CVSS6.3AI score0.00069EPSS
Exploits0References3
RedhatCVE
RedhatCVE
added 2026/06/05 7:49 p.m.6 views

CVE-2026-30615

A prompt injection vulnerability in Windsurf 1.9544.26 allows remote attackers to execute arbitrary commands on a victim system. When Windsurf processes attacker-controlled HTML content, malicious instructions can cause unauthorized modification of the local MCP configuration and automatic...

8CVSS6.4AI score0.0026EPSS
Exploits0References1
NVD
NVD
added 2026/04/15 4:16 p.m.2 views

CVE-2026-30615

A prompt injection vulnerability in Windsurf 1.9544.26 allows remote attackers to execute arbitrary commands on a victim system. When Windsurf processes attacker-controlled HTML content, malicious instructions can cause unauthorized modification of the local MCP configuration and automatic...

8CVSS0.0026EPSS
Exploits0References1
Packet Storm News
Packet Storm News
added 2026/04/02 12:0 a.m.2 views

From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers

The model context protocol MCP standardizes how LLMs connect to external tools and data sources, enabling faster integration but introducing new attack vectors. Despite the growing adoption of MCP, existing MCP security studies classify attacks by their observable effects, obscuring how attacks...

5.8AI score
Exploits0
CNNVD
CNNVD
added 2025/12/17 12:0 a.m.3 views

Zed 命令注入漏洞

Zed is an open source code editor from Zed Industries. A command injection vulnerability exists in versions prior to Zed 0.218.2-pre that stems from loading a malicious MCP configuration from the settings.json file in the project.zed subdirectory, which could lead to arbitrary code execution...

7.7CVSS8AI score0.00252EPSS
Exploits1References3
CVE
CVE
added 2025/12/03 6:34 p.m.14 views

CVE-2025-66222

DeepChat (0.5.0 and earlier) is affected by a Stored XSS in the Mermaid diagram renderer, exploitable via the Electron IPC bridge to escalate to RCE by starting a malicious MCP server. Affected product/version: DeepChat prior to 0.5.0. Root cause: XSS within Mermaid rendering allows arbitrary Jav...

9.6CVSS5.2AI score0.00509EPSS
Exploits1References2Affected Software1
NVD
NVD
added 2025/11/05 12:15 a.m.2 views

CVE-2025-64109

Cursor is a code editor built for programming with AI. In versions and below, a vulnerability in the Cursor CLI Beta allowed an attacker to achieve remote code execution through the MCP Model Context Protocol server mechanism by uploading a malicious MCP configuration in .cursor/mcp.json file in ...

8.8CVSS0.00378EPSS
Exploits0References1
Packet Storm News
Packet Storm News
added 2025/06/05 12:0 a.m.2 views

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol Ecosystem

The Model Context Protocol MCP is an emerging standard designed to enable seamless interaction between Large Language Model LLM applications and external tools or resources. Within a short period, thousands of MCP services have already been developed and deployed. However, the client-server...

6.9AI score
Exploits0
Rows per page
Query Builder