Critical severity · published May 20, 2025
CVE-2025-46725
Langroid is a Python framework to build large language model (LLM)-powered applications
9.8
CVSS
0.5%
EPSS
No
On KEV
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 vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.5% · higher than 45% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LA
Langroid · Langroid
before 0.53.15 · source: NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2025-46725
CVE.org
https://www.cve.org/CVERecord?id=CVE-2025-46725
Patch
https://github.com/langroid/langroid/commit/0d9e4a7bb3ae2eef8d38f2e970ff916599a2b2a6
Vendor Advisory
https://github.com/langroid/langroid/security/advisories/GHSA-22c2-9gwg-mj59
More from Langroid
10.0
CVE-2026-54769
Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent
9.8
CVE-2026-25879
Langroid has Prompt to SQL Injection, Leading to RCE
9.8
CVE-2025-46724
Langroid is a Python framework to build large language model (LLM)-powered applications
9.6
CVE-2026-25481
Langroid has WAF Bypass Leading to RCE in TableChatAgent
9.3
CVE-2026-54760
Langroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file calls
