Command Injection Vulnerability in Langroid Framework by Langroid
CVE-2025-46725

8.1HIGH

Key Information:

Vendor

Langroid

Status
Langroid
Vendor
CVE Published:
20 May 2025

What is CVE-2025-46725?

The Langroid Framework, utilized for developing applications powered by large language models, had a serious command injection vulnerability prior to version 0.53.15. In affected versions, the LanceDocChatAgent component improperly utilized the pandas eval() function within compute_from_docs(), potentially allowing an attacker to execute arbitrary commands on the host system. Version 0.53.15 mitigates this risk by implementing input sanitization for this function by default and includes clear warnings regarding the associated risks in its documentation.

Affected Version(s)

langroid < 0.53.15

References

https://github.com/langroid/langroid/security/advisories/...
x_refsource_CONFIRM
https://github.com/langroid/langroid/commit/0d9e4a7bb3ae2...
x_refsource_MISC

CVSS V4

Score:
8.1
Severity:
HIGH
Confidentiality:
High
Integrity:
High
Availability:
High
Attack Vector:
Network
Attack Complexity:
Low
Attack Required:
None
Privileges Required:
Undefined
User Interaction:
None

Timeline

  • Vulnerability published

  • Vulnerability Reserved

.
CVE-2025-46725 : Command Injection Vulnerability in Langroid Framework by Langroid