Indirect prompt injection in RAG
Learn how Indirect Prompt Injection attacks turn your own data against your LLM, and how to secure RAG pipelines using static analysis.
2 docs tagged with "injection"
View all tagsKeras Lambda Injection: Arbitrary Code Execution via Model Architecture
An architectural breakdown of how Keras Lambda layers serialize Python bytecode within HDF5 files, resulting in RCE during the model graph compilation phase.