Skip to content
Fencer Vulns
critical 10.0

CVE-2026-54769 json

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

published 2026-07-06 4 mo ago modified 2026-07-13 3 mo ago also EUVD-2026-42755 , GHSA-q9p7-wqxg-mrhc , PYSEC-2026-2581

cvss
10.0
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.9%
EPSS 0.9% chance of exploitation in 30 days, percentile 60%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi langroid 0.65.2
  • langroid langroid 0.65.2

CISA SSVC

Exploitation
Proof of concept is public
Automatable
yes
Technical impact
total
Assessed
4 mo ago

Exploit prediction

0.91% chance of exploitation in the next 30 days, higher than 60% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • github.com https://github.com/langroid/langroid/security/advisories/GHSA-q9p7-wqxg-mrhc referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 10.0 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
GitHub 3.1 10.0 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
OSV 3.1 10.0 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Affected packages

ecosystem package affected fixed in
pypi langroid
<0.65.2
0.65.2

Affected products

  • langroid langroid

Classification

Weakness
  • CWE-94 Improper Control of Generation of Code

References

Sources

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.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.