All vulnerabilities
CVE-2024-46946GHSA-p2qj-r53j-h3xjPYSEC-2026-374

langchain-experimental: LangChain Experimental Eval Injection vulnerability

n/a langchain-experimentalpipLibraries & packages
Open in ThreatlineRecord JSON
CVSS
9.3Critical
ExploitationPublic exploit codeCISA's assessment says proof of concept code is public, assessed 19 Sep 2024. Not in the KEV catalogCISA via CVE List
Exploit odds (EPSS)1.39%Chance of exploitation activity in the next 30 days, higher than 72% of CVEs. Scored 27 Oct 2026FIRST EPSS
Fixed inNone listedNo source names a fixed version. Check the vendor advisory below
Published19 Sep 2024Updated 27 Oct 2026CVE List

What fixes it

No source in this snapshot names a fixed version. The vendor advisories under References are the place to check.

Description

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).

Text from CVE List

Affected versions 5

  • langchain-experimental, pip>= 0.1.17, <= 0.3.0GitHub
  • n/aaffected: n/aCVE List
  • langchain-experimental, PyPIfrom 0.1.17, through 0.3.0OSV
  • langchain-experimental, PyPI0.3.0OSV
  • langchain-experimental, PyPI0.3.0.dev1OSV

References 8