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...

PT-2026-64084

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...

GHSA-3PVH-63GF-J9MW 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...

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...

Arbitrary Command Injection

Overview langbot is an Easy-to-use global IM bot platform designed for LLM era Affected versions of this package are vulnerable to Arbitrary Command Injection via the MCP configuration process. An attacker can execute arbitrary commands on the server by submitting specially crafted input to the...

PT-2026-49607

Name of the Vulnerable Software and Affected Versions LangBot versions 4.10.7 and earlier Description Authenticated users can execute arbitrary commands on the server with the privileges of the LangBot service due to an inadequate authorization boundary when adding or changing an STDIO MCP server...

Anthropic MCP Design Vulnerability Enables RCE, Threatening AI Supply Chain

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. "This flaw enables Arbitrary Command Execution R...

CVE-2026-28509

LangBot is a global IM bot platform designed for LLMs. Prior to version 4.8.7, LangBot’s web UI renders user-supplied raw HTML using rehypeRaw, which can lead to a cross-site scripting XSS vulnerability. This issue has been patched in version 4.8.7...

CVE-2026-28509

LangBot is a global IM bot platform designed for LLMs. Prior to version 4.8.7, LangBot’s web UI renders user-supplied raw HTML using rehypeRaw, which can lead to a cross-site scripting XSS vulnerability. This issue has been patched in version 4.8.7...

CVE-2026-28509 LangBot has a Cross Site Scripting(XSS) Vulnerability

LangBot is a global IM bot platform designed for LLMs. Prior to version 4.8.7, LangBot’s web UI renders user-supplied raw HTML using rehypeRaw, which can lead to a cross-site scripting XSS vulnerability. This issue has been patched in version 4.8.7...

CVE-2026-28509 LangBot has a Cross Site Scripting(XSS) Vulnerability

LangBot is a global IM bot platform designed for LLMs. Prior to version 4.8.7, LangBot’s web UI renders user-supplied raw HTML using rehypeRaw, which can lead to a cross-site scripting XSS vulnerability. This issue has been patched in version 4.8.7...

EUVD-2026-9985

LangBot is a global IM bot platform designed for LLMs. Prior to version 4.8.7, LangBot’s web UI renders user-supplied raw HTML using rehypeRaw, which can lead to a cross-site scripting XSS vulnerability. This issue has been patched in version 4.8.7...

CVE-2026-28509

LangBot’s web UI prior to version 4.8.7 renders user-supplied raw HTML via rehypeRaw, resulting in a cross-site scripting (XSS) vulnerability. Affected product: LangBot (global IM bot platform for LLMs). Root cause: unescaped user HTML processed by rehypeRaw. Impact (per CVSS): Confidentiality im...

CVE-2026-28509 LangBot has a Cross Site Scripting(XSS) Vulnerability

LangBot is a global IM bot platform designed for LLMs. Prior to version 4.8.7, LangBot’s web UI renders user-supplied raw HTML using rehypeRaw, which can lead to a cross-site scripting XSS vulnerability. This issue has been patched in version 4.8.7...

CVE-2026-28509: Improper Neutralization of Input During Web Page Generation

LangBot is a global IM bot platform designed for LLMs. Prior to version 4.8.7, LangBot’s web UI renders user-supplied raw HTML using rehypeRaw, which can lead to a cross-site scripting XSS vulnerability. This issue has been patched in version 4.8.7...

LangBot 跨站脚本漏洞

LangBot is an open-source development platform for large-scale instant messaging robots created by LangBot. Versions of LangBot prior to 4.8.7 contained a cross-site scripting vulnerability. This vulnerability stemmed from the use of rehypeRaw to render the original HTML provided by users, which...

PT-2026-23641

Name of the Vulnerable Software and Affected Versions LangBot versions prior to 4.8.7 Description LangBot is a global IM bot platform designed for LLMs. Prior to version 4.8.7, the web UI renders user-supplied raw HTML using rehypeRaw, which can lead to a cross-site scripting XSS issue...

CVE-2025-59835

LangBot is a global IM bot platform designed for LLMs. In versions 4.1.0 up to but not including 4.3.5, authorized attackers can exploit the /api/v1/files/documents interface to perform arbitrary file uploads. Since this interface does not strictly restrict the storage directory of files on the...

CVE-2025-59835

LangBot is a global IM bot platform designed for LLMs. In versions 4.1.0 up to but not including 4.3.5, authorized attackers can exploit the /api/v1/files/documents interface to perform arbitrary file uploads. Since this interface does not strictly restrict the storage directory of files on the...

CVE-2025-59835 LangBot has a cross-directory file upload vulnerability, which could lead to system takeover

LangBot is a global IM bot platform designed for LLMs. In versions 4.1.0 up to but not including 4.3.5, authorized attackers can exploit the /api/v1/files/documents interface to perform arbitrary file uploads. Since this interface does not strictly restrict the storage directory of files on the...