Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1336 CNY

100%
Buy Us a Coffee

CVE-2026-55546— QWED-MCP: Unsafe SymPy `parse_expr()` Remote Code Execution via Unsanitized Math Expression Input

Quick assessment

Affected
QWED-AI qwed-mcp
Exploitation
Public or AI PoC available; prioritize validation
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

QWED-MCP 是一个用于 MCP（Model Context Protocol）的确定性验证网关。在版本 0.2.1 之前， 中的 函数存在安全漏洞。该函数在将攻击者控制的表达式字符串和声称结果字符串传递给 SymPy 的 函数之前，仅将脱字号（caret）语法标准化为 Python 的幂运算语法，但未对全局字典（global_dict）进行限制，未移除 Python 内置函数，也未对表达式的抽象语法树（AST）进行验证。 由于 在调用时会启用内置函数并使用 Python 的 功能，因此，如果攻击者能够促使下游

CVSS 9.8 · Critical EPSS 0.41% · P34

Possible ATT&CK Techniques 1 AI

T1059 · Command and Scripting Interpreter

Affected Version Matrix 1

VendorProduct Version RangeStatus
QWED-AI qwed-mcp < 0.2.1 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-55546

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
QWED-MCP: Unsafe SymPy `parse_expr()` Remote Code Execution via Unsanitized Math Expression Input
Source: CVE Program / CVE List V5
Vulnerability Description
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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
对生成代码的控制不恰当(代码注入)
Source: CVE Program / CVE List V5

Affected Products

Vendor Product Affected Versions CPE Subscribe
QWED-AI qwed-mcp < 0.2.1 -

II. Public POCs for CVE-2026-55546

# POC Description Source Link Shenlong Link
AI-Generated POC Premium
Qwen3.6-35B-A3B · 7882 chars
Pro+ exclusive includes:
Vulnerability reproduction recording (real sandbox build + trigger, exclusive)
In-depth vulnerability mechanism
Trigger conditions & impact
Full executable POC code
Exploit chain & mitigation
POC zip download
100+ AI POC generations per month

III. Intelligence Information for CVE-2026-55546

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-55546 (3)

Vendor Advisories for CVE-2026-55546 (1)

IV. Related Vulnerabilities

Same vendor: QWED-AI
Same weakness: CWE-94

V. Comments for CVE-2026-55546

No comments yet

Leave a comment