Skip to content
LangChainGHSA-p2qj-r53j-h3xj

LangChain Experimental Eval Injection vulnerability

Critical9.8CVE-2024-46946 · Published Sep 19, 2024 · updated Jun 29, 2026

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).

GitHub advisory

Affected versions

PackageAffectedFixed in
langchain-experimental
PyPI
>= 0.1.17, <= 0.3.0No fix yet
Details and references

More LangChain advisories

All LangChain
Advisory
@langchain/community SQL Injection vulnerability
Low4.9Oct 29, 2024
Langchain Path Traversal vulnerability
Medium6.5Oct 29, 2024
Langchain SQL Injection vulnerability
Low4.9Oct 29, 2024
LangChain pickle deserialization of untrusted data
High5.2Sep 17, 2024
langchain-experimental vulnerable to Arbitrary Code Execution
Critical8.5Jul 15, 2024
langchain_experimental Code Execution via Python REPL access
High7.8Jun 16, 2024

Critical advisories by email

Wednesdays: the week’s critical and high advisories in the AI and data stack, with the fixed versions. Only in weeks that have some.

Double opt-in. Unsubscribe any time.