QWED-AI QWED-MCP up to 0.2.0 Math Engine math_engine.py verify_math_expression code injection

Summaryinfo

A vulnerability, which was classified as critical, has been found in QWED-AI QWED-MCP up to 0.2.0. Impacted is the function verify_math_expression of the file src/qwed_mcp/engines/math_engine.py of the component Math Engine. The manipulation leads to code injection. This vulnerability is documented as CVE-2026-55546. The attack can be initiated remotely. There is not any exploit available.

Detailsinfo

A vulnerability was found in QWED-AI QWED-MCP up to 0.2.0. It has been rated as critical. This issue affects the function verify_math_expression of the file src/qwed_mcp/engines/math_engine.py of the component Math Engine. The manipulation with an unknown input leads to a code injection vulnerability. Using CWE to declare the problem leads to CWE-94. The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment. Impacted is confidentiality, integrity, and availability. The summary by CVE is:

QWED-MCP is a deterministic verification gateway for MCP. Prior to 0.2.1, verify_math_expression() in src/qwed_mcp/engines/math_engine.py passes attacker-controlled expression and claimed_result strings directly to SymPy's parse_expr() after only normalizing caret syntax to Python exponent syntax, without restricting global_dict, removing Python built-ins, or validating the expression AST. Because parse_expr() calls Python's eval() with built-ins available, an attacker who can cause a downstream caller to pass untrusted input to this public library function can use Python import functionality to execute arbitrary operating-system commands as the qwed-mcp process user, read or modify accessible data, exfiltrate process secrets, or reach internal services. The default MCP tool registry does not expose verify_math_expression(), so exploitation requires a downstream integration that invokes the library API with attacker-controlled input. This issue is fixed in version 0.2.1.

The advisory is shared at github.com. The identification of this vulnerability is CVE-2026-55546 since 06/17/2026. The exploitation is known to be easy. The attack may be initiated remotely. No form of authentication is needed for a successful exploitation. Technical details are known, but no exploit is available. MITRE ATT&CK project uses the attack technique T1059 for this issue.

Upgrading to version 0.2.1 eliminates this vulnerability.

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• QWED-AI

Name

• QWED-MCP

Version

• 0.1
• 0.2.0

Website

• Product: https://github.com/QWED-AI/qwed-mcp/

CPE 2.3info

• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Discussion