CVE-2025-54135

Below is a fully functional exploit for the CVE-2025-54135 vulnerability in the Cursor IDE, designed to demonstrate a prompt-injection attack that manipulates the Model Context Protocol MCP configuration to achieve remote code execution. This code assumes the attacker has access to a public Slack...

cve-2026-23744

CVE-2026-23744 – MCPJam Inspector Unauthenticated Remote Code Execution RCE Description Product : MCPJam Inspector Affected versions : ≤ 1.4.2 Fixed version : 1.4.3 Type : Unauthenticated Remote Code Execution RCE Attack vector : Network Authentication required : No User interaction required : No...

CVE-2026-9186

IBM Langflow OSS versions 1.0.0 through 1.11.2 contain an improper access control vulnerability (CWE-284) in the MCP configuration installation endpoint. The endpoint enforces a localhost-only restriction using a client IP helper that blindly trusts the X-Forwarded-For header without verifying th...

Security Bulletin: Langflow is vulnerable to stored cross-site scripting and IP spoofing due to unsanitized Markdown rendering and untrusted proxy header trust

Summary Langflow contains two vulnerabilities affecting client-side security and access control integrity. The MarkdownField component renders chat messages using the rehypeRaw plugin without a sanitization pass, causing attacker-controlled LLM response text containing raw HTML to be inserted...

CVE-2026-37006

A vulnerability in the WebSocket endpoint of gpt-researcher v0.14.7 and before allows an unauthenticated remote attacker to achieve code execution via malicious Model Context Protocol configurations...

Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers

Cybersecurity researchers have disclosed details of a vulnerability in Amazon Kiro, an artificial intelligence AI-powered, agentic integrated development environment IDE, that could facilitate data exfiltration via prompt injection and Kiro Powers. The security flaw, which does not have a CVE...

CVE-2026-37006

gpt-researcher v0.14.7 and before is affected by a vulnerability in its WebSocket endpoint that allows an unauthenticated remote attacker to achieve code execution by supplying malicious Model Context Protocol (MCP) configurations . The CNA-assigned CVSS 3.1 score is 9.8 (Critical) with a vector ...

CVE-2026-37006

A vulnerability in the WebSocket endpoint of gpt-researcher v0.14.7 and before allows an unauthenticated remote attacker to achieve code execution via malicious Model Context Protocol configurations...

CVE-2026-54449 LangBot: Authenticated RCE Via MCP Configuration

LangBot is a global IM bot platform designed for LLMs. In version 4.10.7 and earlier, any authenticated user can add or change an STDIO MCP server configuration without an adequate authorization boundary. In src/langbot/pkg/provider/tools/loaders/mcp.py, StdioServerParameters accepts the configur...

PYSEC-2026-3473 LangBot: Authenticated RCE Via MCP Configuration

Summary Any authenticated user can achieve arbitrary command execution on the LangBot servers through changing the MCP Server Configuration by added an "STDIO" MCP with an arbitrary command. Details The repository uses StdioServerParameters which is based on Anthropic's modelcontextprotocol open...

EUVD-2026-45217

ForgeCode tailcallhq/forgecode, an AI pair-programming CLI, automatically loads and executes the MCP servers defined in a repository's .mcp.json file on startup without user confirmation. A malicious repository can supply a crafted .mcp.json whose mcpServers entries specify arbitrary command and...

LangBot: Authenticated RCE Via MCP Configuration

Summary Any authenticated user can achieve arbitrary command execution on the LangBot servers through changing the MCP Server Configuration by added an "STDIO" MCP with an arbitrary command. Details The repository uses StdioServerParameters which is based on Anthropic's modelcontextprotocol open...

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...

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...

CVE-2026-30624

Agent Zero 0.9.8 exposes a remote code execution (RCE) condition via its External MCP Servers configuration. The feature lets users define MCP servers with a JSON config that includes arbitrary command and args values, which are executed when the configuration is applied without sufficient valida...

CVE-2025-68433 Zed IDE MCP Context Server Configuration Arbitrary Code Execution

Zed, a code editor, has an aribtrary code execution vulnerability in versions prior to 0.218.2-pre. The Zed IDE loads Model Context Protocol MCP configurations from the settings.json file located within a project’s .zed subdirectory. A malicious MCP configuration can contain arbitrary shell...

CVE-2025-64109

Cursor CLI Beta contains a vulnerability where uploading a malicious MCP configuration in .cursor/mcp.json in a GitHub repo can trigger remote code execution when a victim clones the project and runs Cursor CLI. The issue results from the MCP (Model Context Protocol) server mechanism executing th...

EUVD-2025-19433

Malicious code in bioql PyPI...

Cursor <= 1.2.1 RCE (GHSA-4cxx-hrm3-49rm)

The version of Cursor installed on the remote host is 1.2.1 or prior. It is, therefore, affected by a remote code execution vulnerability. An attacker could achieve remote and persistent code execution by modifying an already trusted MCP configuration file inside a shared GitHub repository or...

Cursor < 1.2.4 RCE (GHSA-24mc-g4xr-4395)

The version of Cursor installed on the remote host is prior to 1.2.4. It is, therefore, affected by a remote code execution vulnerability. Attackers can achieve remote and persistent code execution by modifying an already trusted MCP configuration file inside a shared GitHub repository or editing...