---
title: "CVE-2026-54769: Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent"
url: https://erroneo.us/security/cve/CVE-2026-54769/
description: "CVE-2026-54769 (langroid (PyPI)): Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to…"
type: vulnerability-record
section: "Security Digest"
date_published: 2026-07-09
date_modified: 2026-07-10
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2026-54769"
kev: false
cvss: 10
epss: 0.00912
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2026-54769: Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent

**Signal:** Critical and remotely reachable. No known exploitation yet, but it is network-reachable without credentials. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- Not in CISA KEV , but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 0.9% , percentile 60: FIRST’s model estimates a 0.9% chance of exploitation activity in the next 30 days, higher than 60% 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 langroid (PyPI) <= 0.65.1, fixed in 0.65.2 . Check your lockfile, including transitive dependencies.

## What it is

Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its TableChatAgent and VectorStore capabilities. When these agents evaluate LLM-generated tool messages with fulleval=True, they attempt to sandbox the execution by explicitly setting locals to an empty dictionary {} inside Python's eval() function. However, this relies on an incomplete understanding of Python's execution model. Because builtins is not explicitly scrubbed from the globals dictionary mapping, Python implicitly injects all built-ins during execution, granting full access to functions like import('os').system(). Since TableChatAgent.pandaseval() executes external LLM outputs natively, this bypass permits any attacker providing prompt payload to achieve unauthenticated RCE on the host system. Version 0.65.2 patches the issue.

## Affected packages

- PyPI `langroid` <= 0.65.1 → fixed: 0.65.2

## Affected products (CVE record)

- langroid langroid: < 0.65.2

## Severity

- GitHub_M CVSS 3.1: 10 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`
- GitHub CVSS 3.1: 10.0 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`

## Exploitation

- 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): 0.91% probability of exploitation activity in the next 30 days; percentile 60.

## Sources

- [GitHub Advisory GHSA-q9p7-wqxg-mrhc](https://github.com/advisories/GHSA-q9p7-wqxg-mrhc)
- [CVE.org record CVE-2026-54769](https://www.cve.org/CVERecord?id=CVE-2026-54769)
- [NVD entry CVE-2026-54769](https://nvd.nist.gov/vuln/detail/CVE-2026-54769)
- [github.com](https://github.com/langroid/langroid/security/advisories/GHSA-q9p7-wqxg-mrhc)

---
Source page: https://erroneo.us/security/cve/CVE-2026-54769/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt