CVE-2023-29374
criticalpriority · attend · 53EPSS 0.397 · 99 %ileEUUSEPSS · scored 2026-10-27
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.
cvss
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
affected products (4)
Products and version ranges known to be affected.
advisories (2)
Vendor and ecosystem advisories describing this.
- GHSA-fprp-p869-w6q2LangChain vulnerable to code injection2023-04-05ghsa · osvUS
In LangChain through 0.0.131, the `LLMMathChain` chain allows prompt injection attacks that can execute arbitrary code via the Python `exec()` method.
- PYSEC-2023-182023-04-05vendor · osvUS
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.
also known as (6)
Other names and identifiers for this entity.
sources
Which sources assert this record, and when.
references (14)
External citations — patches, advisories, analysis.
- https://cxsecurity.com/cveshow/CVE-2023-29374/cnnvd
- https://github.com/hwchase17/langchain/issues/1026cnnvd
- https://github.com/hwchase17/langchain/issues/814cnnvd
- https://github.com/hwchase17/langchain/pull/1119cnnvd
- https://github.com/hwchase17/langchain/releases/tag/v0.0.132Patchcnnvd
- https://twitter.com/rharang/status/1641899743608463365/photo/1cnnvd
- https://github.com/hwchase17/langchain/issues/1026enisa_euvd
- https://github.com/hwchase17/langchain/issues/814enisa_euvd
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan