CVE-2026-25481

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.59.32, there is a bypass to the fix for CVE-2025-46724. TableChatAgent can call pandaseval tool to evaluate the expression. There is a WAF in langroid/utils/pandasutils.py introduced to block code...

CVE-2026-25481

Langroid CVE-2026-25481: Prior to 0.59.32, TableChatAgent bypasses the fix for CVE-2025-46724 by enabling pandas_eval with unrestricted access to dangerous dunder attributes. This allows chaining DataFrame methods to leak eval and execute arbitrary code. The issue is patched in version 0.59.32. A...

CVE-2026-25481 Langroid has WAF Bypass Leading to RCE in TableChatAgent

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.59.32, there is a bypass to the fix for CVE-2025-46724. TableChatAgent can call pandaseval tool to evaluate the expression. There is a WAF in langroid/utils/pandasutils.py introduced to block code...

Langroid 代码注入漏洞

Langroid is an open-source tool developed using multi-agent programming for LLM tasks. Versions of Langroid prior to 0.59.32 had a code injection vulnerability. This vulnerability stemmed from a bypass in the TableChatAgent’s invocation of the pandaseval tool, which could allow arbitrary code to ...

Langroid has WAF Bypass Leading to RCE in TableChatAgent

Affected Scope langroid = 0.59.31 Vulnerability Description CVE-2025-46724 fix bypass: TableChatAgent can call pandaseval tool to evaluate the expression. There is a WAF in langroid/utils/pandasutils.py introduced to block code injection CVE-2025-46724. However it can be bypassed due to literalok...

Arbitrary Code Injection

Overview langroid is a Harness LLMs with Multi-Agent Programming Affected versions of this package are vulnerable to Arbitrary Code Injection via the pandaseval function. An attacker can execute arbitrary code by supplying crafted input that bypasses input validation and leverages access to...

GHSA-X34R-63HX-W57F Langroid has WAF Bypass Leading to RCE in TableChatAgent

Affected Scope langroid = 0.59.31 Vulnerability Description CVE-2025-46724 fix bypass: TableChatAgent can call pandaseval tool to evaluate the expression. There is a WAF in langroid/utils/pandasutils.py introduced to block code injection CVE-2025-46724. However it can be bypassed due to literalok...

EUVD-2025-15952

Malicious code in bioql PyPI...

EUVD-2025-13410

Malicious code in bioql PyPI...

EUVD-2025-15951

Malicious code in bioql PyPI...

Arbitrary Code Execution

Langroid is vulnerable to Arbitrary Code Execution. The vulnerability is due to unsafe code evaluation due to the use of pandas.eval in the LanceDocChatAgent via the computefromdocs function, allowing attackers to execute malicious code through unsanitized input...

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 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...

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 (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-2025-46725 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...