Vulnerabilitycritical
Anthropic MCP Design Vulnerability Enables RCE, Threatening AI Supply Chain
Vulnerabilities mentioned
All| CVE | Vulnerability | CVSS | EPSS | Signals | Published |
|---|---|---|---|---|---|
| CVE-2025-49596 | Unauthenticated RCE in Anthropic MCP Inspector (versions below 0.14.1) | 9.4 | 43% | ||
| CVE-2025-54136 | Trusted MCP Config Swap Enables RCE in Cursor AI Code Editor ≤1.2.4 | 8.8 | 27% | ||
| CVE-2025-54994 | @akoskm/create-mcp-server-stdio is an MCP server starter kit that uses the StdioServerTransport | 9.3 | 1% | ||
| CVE-2025-65720 | An issue in Open Source GPT Researcher v3.3.7 allows attackers to execute arbitrary commands on a victim system via user interaction with a crafted HTML page | 9.8 | <1% | ||
| CVE-2026-22252 | LibreChat: LibreChat's MCP stdio transport accepts arbitrary commands without validation, allowing any authenticated user to execute shell… | 9.9 | 4% | PoC | |
| CVE-2026-22688 | WeKnora: There is a command injection vulnerability that allows authenticated users to inject stdio_config.command/args into MCP stdio… | 8.8 | 2% | PoC | |
| CVE-2026-26015 | DocsGPT: An attacker accessing both the official DocsGPT website or any local and public deployment, can craft a malicious payload… | 10.0 | 1% | PoC | |
| CVE-2026-30615 | A prompt injection vulnerability in Windsurf 1.9544.26 allows remote attackers to execute arbitrary commands on a victim system | 8.0 | <1% | ||
| CVE-2026-30617 | LangChain-ChatChat 0.3.1 contains a remote code execution vulnerability in its MCP STDIO server configuration and execution handling | 8.6 | <1% | ||
| CVE-2026-30618 | xszyou Fay 4.3.1 contains a remote code execution vulnerability in its MCP STDIO server management and command execution handling | 9.8 | 1% | ||
| CVE-2026-30623 | LiteLLM 1.18.10 contains a remote code execution vulnerability in its MCP server creation functionality | 9.8 | 5% | ||
| CVE-2026-30624 | Agent Zero 0.9.8 contains a remote code execution vulnerability in its External MCP Servers configuration feature | 8.6 | <1% | ||
| CVE-2026-30625 | Upsonic 0.71.6 contains a remote code execution vulnerability in its MCP server/task creation functionality | 9.8 | <1% | ||
| CVE-2026-40933 | Flowise: Due to unsafe serialization of stdio commands in the MCP adapter, an authenticated attacker can add an MCP stdio server with an… | 9.9 | 12% | PoC |
From the original article
2 min read at thehackernews.com
Ravie Lakshmanan Apr 20, 2026 Artificial Intelligence / Vulnerability Cybersecurity researchers have discovered a critical "by design" weakness in the Model Context Protocol's ( MCP ) architecture that could pave the way for remote code execution and have a cascading effect on the artificial intelligence (AI) supply chain.
By @TheHackersNews · thehackernews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.