CVE-2025-46725CRITICAL 9.8EPSS p37.7%

CVE-2025-46725CVE-2025-46725

Description

Langroid is a Python framework to build large language model (LLM)-powered applications. Prior to version 0.53.15, `LanceDocChatAgent` uses pandas eval() through `compute_from_docs()`. As a result, an attacker may be able to make the agent run malicious commands through `QueryPlan.dataframe_calc]`) compromising the host system. Langroid 0.53.15 sanitizes input to the affected function by default to tackle the most common attack vectors, and added several warnings about the risky behavior in the project documentation.

Scoring

CVSS 3.19.8 (CRITICAL)
VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS0.48% probability of exploitation · percentile 37.7% · 2026-06-18T12:00:27Z
Published2025-05-20
Last modified2025-08-13

Underlying weaknesses· 1

CWE-94

References

  1. https://github.com/langroid/langroid/commit/0d9e4a7bb3ae2eef8d38f2e970ff916599a2b2a6
  2. https://github.com/langroid/langroid/security/advisories/GHSA-22c2-9gwg-mj59

1

TypeTargetConfidenceTier
WeaknessImproper Control of Generation of Code ('Code Injection')cwe-940%live

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

CVE
CVE-2025-46724
CVE
CVE-2026-25481
CVE
CVE-2025-46726
CVE
CVE-2026-25879
CVE
CVE-2026-27966
CVE
CVE-2026-0769
Sourced from NVD + FIRST.org EPSS. Curated for EU compliance use cases by Adam Lundqvist, Founder at SQUR.