CVE-2026-55546 json
QWED-MCP: Unsafe SymPy `parse_expr()` Remote Code Execution via Unsanitized Math Expression Input
published 2026-08-25 2 mo ago modified 2026-09-10 1 mo ago also GHSA-mw6r-2hvm-4rp2 , PYSEC-2026-3915 , EUVD-2026-65547
- cvss
- 9.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.7%
- EPSS 0.7% chance of exploitation in 30 days, percentile 54%
- public exploits
- 0
- none known
Summary
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.
Patch / fix
- pypi qwed-mcp 0.2.1
- github.com/QWED-AI/qwed-mcp@362e618 commit
- github.com/QWED-AI/qwed-mcp#22 pull request
- github.com/QWED-AI/qwed-mcp/releases/tag/v0.2.1 release
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- total
- Assessed
- 2 mo ago
Exploit prediction
0.73% chance of exploitation in the next 30 days, higher than 54% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/QWED-AI/qwed-mcp/security/advisories/GHSA-mw6r-2hvm-4rp2 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| OSV | 3.1 | 9.8 | 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 |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | qwed-mcp | <0.2.1 |
0.2.1 |
Affected products
- QWED-AI qwed-mcp
Classification
- Weakness
-
- CWE-94 Improper Control of Generation of Code
References
-
github.com
/QWED-AI/qwed-mcp/pull/22
web
-
github.com
/QWED-AI/qwed-mcp/commit/362e61892052e250c56cb1ee852024d6f98c467b
web
-
github.com
/QWED-AI/qwed-mcp/security/advisories/GHSA-mw6r-2hvm-4rp2
exploit, web
-
github.com
/QWED-AI/qwed-mcp/releases/tag/v0.2.1
web
-
github.com
/QWED-AI/qwed-mcp
package
-
pypi.org
/project/qwed-mcp
package
-
github.com
/advisories/GHSA-mw6r-2hvm-4rp2
advisory
-
nvd.nist.gov
/vuln/detail/CVE-2026-55546
advisory
Sources
- CVE List CVE-2026-55546
- GitHub Advisory GHSA-mw6r-2hvm-4rp2
- NVD CVE-2026-55546
- OSV PYSEC-2026-3915
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.