An issue in Harrison Chase langchain v.0.0.194 and before allows a remote attacker to execute arbitrary code via the from_math_prompt and from_colored_object_prompt functions.
The product constructs all or part of a command, data structure, or record using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify how it is parsed or interpreted when it is sent to a downstream component.
Link | Tags |
---|---|
https://github.com/hwchase17/langchain/issues/5872 | patch issue tracking exploit |
https://github.com/hwchase17/langchain/pull/6003 | patch |
https://twitter.com/llm_sec/status/1668711587287375876 | third party advisory |