Live › vulnerability › CVE-2024-46946
Go to dashboardLangChain Experimental versions 0.1.17 through 0.3.0 pass model-generated text to sympy.sympify, which uses eval, inside LLMSymbolicMathChain. An attacker who can steer the model's input can execute arbitrary Python code on the server running the chain.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-27 16:56 UTC, 0h before NVD. All times on this page are UTC.
Applications that import langchain-experimental in this version range and actually run LLMSymbolicMathChain on input that a user or external data source can influence. Teams that do not use this chain, or that run the package only in offline tooling with trusted input, are at much lower risk.
| Product | Ecosystem | Affected | Fixed in |
|---|---|---|---|
| langchain-experimental | pypi | >= 0.1.17, <= 0.3.0 | – |
| langchain langchain-experimental | vendor | >= 0.1.17, <= 0.3.0 | – |
pip show langchain-experimental and check whether the version is between 0.1.17 and 0.3.0LLMSymbolicMathChain to see whether the chain is used at alllangchain-experimental to a version newer than 0.3.0 (the sources do not name the exact fixed version; check the GHSA page)LLMSymbolicMathChain if it is not neededEach row is the first time that source carried this signal. The analyst’s rows are its own findings.
langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify (which uses eval) in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6 (2023-10-05).
This page as .md · .json · in your agent: get_signal("CVE-2024-46946")
GitHub Advisory Database, CC-BY 4.0 · NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.