Lucene search
K

4 matches found

RedhatCVE
RedhatCVE
added 2025/05/22 6:16 p.m.16 views

CVE-2025-46725

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, LanceDocChatAgent uses pandas eval through computefromdocs. As a result, an attacker may be able to make the agent run malicious commands through QueryPlan.dataframecalc compromising t...

9.8CVSS7AI score0.0041EPSS
Exploits0References1
RedhatCVE
RedhatCVE
added 2025/05/22 6:16 p.m.3 views

CVE-2025-46724

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, TableChatAgent uses pandas eval. If fed by untrusted user input, like the case of a public-facing LLM application, it may be vulnerable to code injection. Langroid 0.53.15 sanitizes...

9.8CVSS7.3AI score0.00206EPSS
Exploits1References1
Vulnrichment
Vulnrichment
added 2025/05/20 5:22 p.m.6 views

CVE-2025-46724 Langroid has a Code Injection vulnerability in TableChatAgent

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, TableChatAgent uses pandas eval. If fed by untrusted user input, like the case of a public-facing LLM application, it may be vulnerable to code injection. Langroid 0.53.15 sanitizes...

9.8CVSS9.7AI score0.00206EPSS
Exploits1References2
OSV
OSV
added 2025/05/05 8:40 p.m.8 views

GHSA-PW95-88FG-3J6F Langroid Allows XXE Injection via XMLToolMessage

Summary A LLM application leveraging XMLToolMessage class may be exposed to untrusted XML input that could result in DoS and/or exposing local files with sensitive information. Details XMLToolMessage uses lxml without safeguards:...

8.8CVSS6.5AI score0.00446EPSS
Exploits1References5
Rows per page
Query Builder