Skip to content
TrackCVE
  • Newest CVEsPage
  • Recently added to KEVPage
  • Rising exploitation (EPSS)Page
  • Weekly digestPage
  • StatisticsPage
  • WatchlistPage
  • API documentationPage
  • MCP serverPage
  • Data sourcesPage
  • ChangelogPage
  • AboutPage
  • How it's builtPage
Back

CVE-2026-54769

Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent

Critical10.0Public exploitEPSS 0.91%
Published
Updated
Reserved
Assigned by
GitHub_M

Description

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 `full_eval=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.pandas_eval()` 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.

Public exploit

A reference of the record is tagged as an exploit or proof of concept: anyone can try it against an unpatched system. CISA's SSVC rates its exploitation: a proof of concept is public.

Timeline

  1. ID reserved

    By GitHub_M

  2. · 24 days later

    Published

  3. · 1 day later

    Record updated

Changes after publication (a new score, a public exploit, EPSS crossing 1, 10 or 50 %, leaving KEV) are kept since November 2026; earlier ones are not known.

Scores

CVSS scores of CVE-2026-54769, by who scored it
Scored byCVSSScoreVector
GitHub_MCNA (assigner)3.1Critical10.0CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
NVDNVD · Deferred3.1Critical10.0CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
EPSS (exploitation in 30 days)
0.91% · top 40% of all CVEs (7 Nov 2026)
CISA SSVC
Exploitation: poc · Automatable: yes · Technical impact: total
Loading the EPSS history…

The list uses the assigner's score when there is one, then CISA's, then NVD's: Critical 10.0.

Weakness

Affected products

Affected packages

From reviewed advisories of the GitHub Advisory Database.

References (1)

Sources

The same CVE in the primary databases and aggregators, to check against.

Badge for a README or a ticket

CVE-2026-54769 badge
[![CVE-2026-54769](https://trackcve.app/badge/CVE-2026-54769.svg)](https://trackcve.app/cve/CVE-2026-54769)

Record last updated .