VulnerabilityAnalyzed

CVE-2025-46725

As a result, an attacker may be able to make the agent run malicious commands through `QueryPlan.dataframe_calc]`) compromising the host system.

HIGH 8.1EPSS 0.53%

Does this matter?

High impact if exploited, but EPSS currently rates exploitation as unlikely (0.53%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.

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.

CVSS 4.0: 8.1 HIGHCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:U/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/M
EPSS: 0.53% probability · 43th percentile
CISA KEV: Not listed
Weakness: CWE-94
Affected: langroid/langroid
Source: security-advisories@github.com

References

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.