Security Digest · Vulnerability record
CVE-2026-55546: qwed-mcp has Unsafe SymPy `parse_expr()` Remote Code Execution via Unsanitized Math Expression Input
QWED-MCP is a deterministic verification gateway for MCP.
CVSS 9.8 Critical EPSS 0.7% · p54
Should you act?
Critical and remotely reachable
No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.
- Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 0.7%, percentile 54: FIRST’s model estimates a 0.7% chance of exploitation activity in the next 30 days, higher than 54% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes
qwed-mcp(PyPI) < 0.2.1, fixed in 0.2.1. Check your lockfile, including transitive dependencies.
What it is
QWED-MCP is a deterministic verification gateway for MCP. Prior to 0.2.1, verifymathexpression() in src/qwedmcp/engines/mathengine.py passes attacker-controlled expression and claimedresult strings directly to SymPy's parseexpr() after only normalizing caret syntax to Python exponent syntax, without restricting globaldict, removing Python built-ins, or validating the expression AST. Because parseexpr() 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 verifymathexpression(), so exploitation requires a downstream integration that invokes the library API with attacker-controlled input. This issue is fixed in version 0.2.1.
From the GitHub advisory
Summary
verifymathexpression() in qwed-mcp v0.2.0 passes attacker-controlled strings directly to SymPy's parseexpr() without restricting globaldict or validating the expression's AST. Because parseexpr() 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/qwedmcp/engines/mathengine.py. The public function verifymathexpression(expression, claimedresult, operation) accepts both the expression and claimedresult arguments as raw strings and passes them — after a trivial ^ → substitution — to sympy.parsing.sympyparser.parseexpr():
localdict only adds math symbols to the evaluation namespace; it does not remove builtins. SymPy's parseexpr() eventually calls Python's built-in eval(), which — absent an explicit {"builtins": {}} in globaldict — receives the full built-in namespace. This makes import, open, exec, and every other Python built-in available to the evaluated expression.
Weakness type: CWE-94.
Product: qwed-mcp (PyPI) · Assigned by: GitHub_M · Published: 2026-08-25
Affected and fixed versions
| Ecosystem | Package | Vulnerable | First fixed |
|---|---|---|---|
| PyPI | qwed-mcp | < 0.2.1 | 0.2.1 |
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| QWED-AI | qwed-mcp | < 0.2.1 |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| GitHub_M | 3.1 | 9.8 Critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Privileges required: none (no login)
- User interaction: none
- Scope: unchanged
CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.
Exploitation and urgency
- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc, automatable yes, technical impact total.
- FIRST EPSS (model of 2026-10-21): 0.73% probability of exploitation activity in the next 30 days; percentile 54.
Timeline
- — CVE record last updated
- — CVE record published by GitHub_M
- — GitHub-reviewed advisory GHSA-mw6r-2hvm-4rp2 published (critical)
Sources and references
Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.
Vulnerability records
- GitHub Advisory GHSA-mw6r-2hvm-4rp2 github.com
- CVE.org record CVE-2026-55546 cve.org
- NVD entry CVE-2026-55546 nvd.nist.gov
Other references from the CVE record and advisory
- github.com github.com
- github.com github.com
- github.com github.com
- github.com github.com