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...

Arbitrary Code Injection

Overview langroid is a Harness LLMs with Multi-Agent Programming Affected versions of this package are vulnerable to Arbitrary Code Injection through the computefromdocs process. An attacker can execute arbitrary code by manipulating the input data to the QueryPlan.dataframecalc method. Remediati...

Arbitrary Code Injection

Overview langroid is a Harness LLMs with Multi-Agent Programming Affected versions of this package are vulnerable to Arbitrary Code Injection due to the use of pandas eval function. An attacker can execute arbitrary code by supplying malicious input to this function. This is only exploitable if t...

CVE-2025-46725 Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store

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-2025-46725 Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store

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-2025-46725 Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store

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-2025-46725

Langroid (Python framework for LLM-powered apps) contains a code execution vulnerability in the LanceDocChatAgent prior to version 0.53.15, caused by the use of pandas.eval() in the compute_from_docs() path. An attacker could cause the agent to execute malicious commands via crafted input and rel...

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 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...

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...

PT-2026-6292

Name of the Vulnerable Software and Affected Versions Langroid versions prior to 0.59.32 Description Langroid is a framework used for building applications powered by large-language-models. A weakness exists in the TableChatAgent component where the Web Application Firewall WAF can be bypassed...

Langroid 代码注入漏洞

Langroid is a Langroid open source tool for developing LLMs using multi-agent programming. A code injection vulnerability exists in Langroid versions prior to 0.53.15, which stems from TableChatAgent's use of pandas eval to process unauthenticated user input, which could lead to code injection...

Langroid 代码注入漏洞

Langroid is a Langroid open source tool for developing LLMs using multi-agent programming. A code injection vulnerability exists in Langroid versions prior to 0.53.15, which stems from LanceDocChatAgent processing unauthenticated user input using pandas eval via computefromdocs, which could lead ...

PT-2025-22277

Name of the Vulnerable Software and Affected Versions Langroid versions prior to 0.53.15 Description The issue concerns the use of pandas eval through the compute from docs function in the LanceDocChatAgent component. This allows an attacker to potentially run malicious commands, compromising the...

PT-2025-22276

Name of the Vulnerable Software and Affected Versions Langroid versions prior to 0.53.15 Description The issue concerns Langroid, a Python framework for building large language model LLM-powered applications. In versions prior to 0.53.15, the TableChatAgent uses pandas eval, which may be vulnerab...

CVE-2025-46726

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.53.4, 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. Version 0.53.4 fixes th...

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:...

CVE-2025-46726

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.53.4, 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. Version 0.53.4 fixes th...