CVE-2025-1750: LlamaIndex DuckDBVectorStore vulnerable to SQL injection through ref_doc_id
An SQL injection vulnerability exists in the delete function of DuckDBVectorStore in run-llama/llamaindex version v0.12.19. This vulnerability allows an attacker to manipulate the refdocid parameter, enabling them to read and write arbitrary files on the server, potentially leading to remote code execution (RCE).
Published Jun 2, 2025 · Updated Oct 2, 2026
Affected packages
llama-index-vector-stores-duckdb
- Ecosystem
- PyPI
- Affected
- >= 0.12.19, < 0.12.21
- Fixed in
- 0.12.21
- Check
pip show llama-index-vector-stores-duckdb
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
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).
References
- https://nvd.nist.gov/vuln/detail/CVE-2025-1750
- https://github.com/run-llama/llama_index/commit/369a2942df2efcf6b74461c45d20a0af1fbe4ae2
- https://huntr.com/bounties/e1302233-9180-4269-9047-1526247d2cd8
- https://github.com/pypa/advisory-database/tree/main/vulns/llama-index/PYSEC-2025-245.yaml
- https://github.com/run-llama/llama_index/releases/tag/v0.12.21
- https://github.com/advisories/GHSA-6mcc-q3mg-3qg6
How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology