Answer in brief
CVE-2025-1750 records a Critical severity (CVSS 9.8) vulnerability in LlamaIndex DuckDBVectorStore vulnerable to SQL injection through ref_doc_id. The current sources do not mark it as known exploited. The current feed maps llama-index-vector-stores-duckdb (pip), llama-index (pypi), llama-index-vector-stores-duckdb (pypi). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 9.8. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps llama-index-vector-stores-duckdb (pip), llama-index (pypi), llama-index-vector-stores-duckdb (pypi). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| llama-index-vector-stores-duckdbpip | >=0.12.19,<0.12.21 | 0.12.21 |
| llama-indexpypi | >=0.12.19 <0.12.21 | 0.12.21 |
| llama-index-vector-stores-duckdbpypi | >=0.12.19 <0.12.21 | 0.12.21 |
Published upstream
Jun 2, 2025
Evidence: source:ghsa:source_dates:source-dates:recordSource modified
Oct 2, 2026
Evidence: source:ghsa:source_dates:source-dates:recordFirst seen by HOL
Oct 2, 2026
An SQL injection vulnerability exists in the delete function of DuckDBVectorStore in run-llama/llama_index version v0.12.19. This vulnerability allows an attacker to manipulate the ref_doc_id parameter, enabling them to read and write arbitrary files on the server, potentially leading to remote code execution (RCE).
Quoted source text, attributed separately from HOL analysis.