PyPI package
langroid
pkg:pypi/langroid
Vulnerabilities (5)
| CVE | Sev | CVSS | KEV | Affected versions | Fixed in | Published | Description |
|---|---|---|---|---|---|---|---|
| CVE-2026-25879 | cri | — | < 0.63.0 | 0.63.0 | May 27, 2026 | # Security Vulnerability Report: Prompt to SQL Injection leading to RCE in latest Langroid ## Affected Scope langroid < 0.63.0 ## Vulnerability Description SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database | |
| CVE-2026-25481 | — | < 0.59.32 | 0.59.32 | Feb 4, 2026 | 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 pandas_eval tool to evaluate the expression. There is a WAF in langroid/utils/pandas_utils.py introdu | ||
| CVE-2025-46725 | — | < 0.53.15 | 0.53.15 | May 20, 2025 | Langroid is a Python framework to build large language model (LLM)-powered applications. Prior to version 0.53.15, `LanceDocChatAgent` uses pandas eval() through `compute_from_docs()`. As a result, an attacker may be able to make the agent run malicious commands through `QueryPla | ||
| CVE-2025-46724 | — | < 0.53.15 | 0.53.15 | May 20, 2025 | 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. Lang | ||
| CVE-2025-46726 | — | < 0.53.4 | 0.53.4 | May 5, 2025 | 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. Vers |
- affected < 0.63.0fixed 0.63.0
# Security Vulnerability Report: Prompt to SQL Injection leading to RCE in latest Langroid ## Affected Scope langroid < 0.63.0 ## Vulnerability Description SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database
- CVE-2026-25481Feb 4, 2026affected < 0.59.32fixed 0.59.32
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 pandas_eval tool to evaluate the expression. There is a WAF in langroid/utils/pandas_utils.py introdu
- CVE-2025-46725May 20, 2025affected < 0.53.15fixed 0.53.15
Langroid is a Python framework to build large language model (LLM)-powered applications. Prior to version 0.53.15, `LanceDocChatAgent` uses pandas eval() through `compute_from_docs()`. As a result, an attacker may be able to make the agent run malicious commands through `QueryPla
- CVE-2025-46724May 20, 2025affected < 0.53.15fixed 0.53.15
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. Lang
- CVE-2025-46726May 5, 2025affected < 0.53.4fixed 0.53.4
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. Vers