EUVD-2025-15952

Malicious code in bioql PyPI...

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...

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...

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...

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...

CVE-2025-46724

Langroid CVE-2025-46724 affects TableChatAgent, where untrusted input can trigger code injection via pandas_eval in TableChatAgent prior to v0.53.15. The project added a WAF in pandas_utils.py and warnings, with a patch in v0.59.32 that blocks the bypass. However, subsequent disclosures (CVE-2026...

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:...