Critical severity · published Apr 5, 2023
CVE-2023-29374
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method
9.8
CVSS
39.7%
EPSS
No
On KEV
Description
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)39.7% · higher than 99% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LA
Langchain · Langchain
through 0.0.131 · source: NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2023-29374
CVE.org
https://www.cve.org/CVERecord?id=CVE-2023-29374
Issue Tracking
https://github.com/hwchase17/langchain/issues/1026
Exploit
https://github.com/hwchase17/langchain/issues/814
Patch
https://github.com/hwchase17/langchain/pull/1119
Exploit
https://twitter.com/rharang/status/1641899743608463365/photo/1
More from Langchain
10.0
CVE-2025-2828
SSRF Vulnerability in RequestsToolkit in langchain-ai/langchain
9.8
CVE-2024-8309
SQL Injection in langchain-ai/langchain
9.8
CVE-2024-7042
Prompt Injection in langchain-ai/langchainjs Leading to SQL Injection
9.8
CVE-2024-2057
LangChain langchain_community TFIDFRetriever tfidf.py load_local server-side request forgery
9.8
CVE-2023-39631
An issue in LanChain-ai Langchain v.0.0.245 allows a remote attacker to execute arbitrary code via the evaluate function in the numexpr library