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.
The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.
Link | Tags |
---|---|
https://github.com/hwchase17/langchain/issues/4394 | vendor advisory issue tracking exploit |
https://aisec.today/LangChain-2e6244a313dd46139c5ef28cbcab9e55 | third party advisory exploit |
https://github.com/langchain-ai/langchain/releases/tag/v0.0.312 |