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...

Code Injection

langroid is vulnerable to code injection. The vulnerability is due to improper input sanitization in TableChatAgent using pandas eval, allowing attackers to execute arbitrary code within the application...

GHSA-22C2-9GWG-MJ59 Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store

Summary LanceDocChatAgent uses pandas eval through computefromdocs: https://github.com/langroid/langroid/blob/18667ec7e971efc242505196f6518eb19a0abc1c/langroid/vectorstore/base.pyL136-L150 As a result, an attacker may be able to make the agent run malicious commands through QueryPlan.dataframecal...

Langroid has a Code Injection vulnerability in TableChatAgent

Summary 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. PoC For example, one could prompt the Agent: Evaluate the following pandas expression on the data provided and print output:...

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...

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...

PT-2025-22277 · Langroid · Langroid

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 t...

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 ...