Vulnerability 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 Score
9.8
CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Langchain | Langchain | <= 0.0.131 |
Related Weaknesses (CWE)
References
- https://github.com/hwchase17/langchain/issues/1026Issue Tracking
- https://github.com/hwchase17/langchain/issues/814ExploitIssue TrackingPatch
- https://github.com/hwchase17/langchain/pull/1119Patch
- https://twitter.com/rharang/status/1641899743608463365/photo/1Exploit
- https://github.com/hwchase17/langchain/issues/1026Issue Tracking
- https://github.com/hwchase17/langchain/issues/814ExploitIssue TrackingPatch
- https://github.com/hwchase17/langchain/pull/1119Patch
- https://twitter.com/rharang/status/1641899743608463365/photo/1Exploit
FAQ
What is CVE-2023-29374?
CVE-2023-29374 is a vulnerability with a CVSS score of 9.8 (CRITICAL). In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.
How severe is CVE-2023-29374?
CVE-2023-29374 has been rated CRITICAL with a CVSS base score of 9.8/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2023-29374?
Check the references section above for vendor advisories and patch information. Affected products include: Langchain Langchain.