Improper input validation in Langchain Langchain-Experimental
CVE-2024-46946
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).
Vulnerability class: Drupalgeddon 2 (CVE-2018-7600)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS: 0.014 (71.2th percentile), scored .
Low probability of exploitation in the next 30 days, but still tracked. 71st percentile — 71.2% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.014 · newest: 0.014 · change: 0.000
Affected products
Weakness classification (CWE)
Public proof-of-concept exploits
References
- cwe.mitre.org/data/definitions/95.html (Not Applicable)
- github.com/langchain-ai/langchain/releases/tag/langchain-experimental==0.3.0 (Release Notes)
- docs.sympy.org/latest/modules/codegen.html (Technical Description)
- gist.github.com/12end/68c0c58d2564ef4141bccd4651480820 (Exploit, Third Party Advisory)
Frequently asked questions
- What is CVE-2024-46946?
- CVE-2024-46946 is a critical-severity vulnerability in Langchain Langchain-Experimental, classified under Improper Input Validation. CVSS score: 9.8/10. Published 2024-09-19.
- How severe is CVE-2024-46946?
- Critical severity. CVSS v3 base score is 9.8 out of 10.
- Is CVE-2024-46946 known to be exploited?
- 1 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.