LangGrinch: LangChain Core Serialization Injection
A real design flaw in a library almost every Python agent stack pulls in, but it needs a serialize-then-deserialize path over attacker-influenced data; bump langchain-core in your next routine dependency update.
Must act: Teams running LangChain apps that stream events with astream_events v1 or astream_log, persist message history, or load serialized objects that can contain LLM output or user data.
Can relax: Projects that never call LangChain's load()/loads() on data that could contain model output or user input, or that already run langchain-core 1.2.5+ or 0.3.81+.
- Upgrade Python langchain-core to 1.2.5 (1.x) or 0.3.81 (0.3.x): pip install -U 'langchain-core>=1.2.5'
- Upgrade JS @langchain/core to 1.1.8 or 0.3.80 and langchain to 1.2.3 or 0.3.37
- Move streaming code from astream_events(version="v1") to version="v2"