An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a JSON file to load_prompt. This is related to __subclasses__ or a template.
References
Link | Resource |
---|---|
https://aisec.today/LangChain-2e6244a313dd46139c5ef28cbcab9e55 | Exploit Third Party Advisory |
https://github.com/hwchase17/langchain/issues/4394 | Exploit Issue Tracking Vendor Advisory |
https://github.com/langchain-ai/langchain/releases/tag/v0.0.312 |
Configurations
History
No history.
Information
Published : 2023-08-22 19:16
Updated : 2023-11-29 01:15
NVD link : CVE-2023-36281
Mitre link : CVE-2023-36281
CVE.ORG link : CVE-2023-36281
JSON object : View
Products Affected
langchain
- langchain
CWE
CWE-94
Improper Control of Generation of Code ('Code Injection')