Browse / RAG and Vector Store Weaknesses / SQL and query injection
SQL and query injection
8 records in RAG and Vector Store Weaknesses.
- mem0ai Databricks vector store vulnerable to SQL injection Stored memory text or metadata reaches unescaped string interpolation in the Databricks vector store's insert and update statements, so attacker-chosen SQL runs on the warehouse.
- PraisonAI: PGVector and Cassandra knowledge stores interpolate vector dimensions into DDL
- Open WebUI: RAG ACL Bypass in Milvus Multitenancy Mode
- agno contains a SQL injection vulnerability Metadata keys and values passed to the ClickHouse vector store delete method are interpolated into SQL, letting attackers alter queries and read data.
- PraisonAI knowledge-store backends interpolate unvalidated collection names into SQL and CQL queries Collection names passed to SQL and CQL knowledge-store backends are concatenated into table and index identifiers without validation, enabling query injection.
- Vanna has a SQL injection in the remove_training_data function The ID argument of a BigQuery vector store delete function is concatenated into SQL, letting callers inject query clauses.
- llama_index vulnerable to SQL Injection
- LlamaIndex Retrievers Integration: DuckDBRetriever SQL Injection Untrusted query text is concatenated into DuckDB SQL, letting an attacker load the shellfs extension and run OS commands.