CVE-2025-1750: Llama index vector stores duckdb SQL Injection Vulnerability

CRITICAL
Advisory Identifier: GHSA-6mcc-q3mg-3qg6
CVSS 9.8
CWE-89
Published
Advisory Summary

CVE-2025-1750 is a CRITICAL (CVSS 9.8) sql injection vulnerability (CWE-89: Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection')) affecting Llama index vector stores duckdb libraries in the PyPI ecosystem. The issue involves llamaindex duckdbvectorstore vulnerable to sql injection through ref_doc_id. Remediation is available by upgrading affected packages to version 0.12.21.

CVE-2025-1750 at a Glance

CVE Identifier CVE-2025-1750
GHSA Identifier GHSA-6mcc-q3mg-3qg6
Severity CRITICAL
CVSS v3.1 Base Score 9.8
CWE Classification CWE-89: Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection')
Affected Product Llama index vector stores duckdb
Package Ecosystem PyPI
Published Date
Last Updated

Security Impact

CVSS: 9.8

The security impact metrics below are parsed directly from the CVSS v3.1 vector string (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H).

Attack Vector Network (AV:N)
Attack Complexity Low (AC:L)
Privileges Required None (PR:N)
User Interaction None (UI:N)
Scope Unchanged (S:U)
Confidentiality High (C:H)
Integrity High (I:H)
Availability High (A:H)

How to Fix CVE-2025-1750

To remediate this vulnerability, upgrade all affected Llama index vector stores duckdb dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.

llama-index-vector-stores-duckdb fixed: 0.12.21
pip install llama-index-vector-stores-duckdb>=0.12.21
Verify Direct and Transitive Dependencies

Run the following command in your project directory to verify that all resolved dependencies use the patched release:

pip show llama-index-vector-stores-duckdb

How to Check if You Are Affected

To determine whether your Python environment is affected by CVE-2025-1750, inspect your installed packages using pip:

pip show llama-index-vector-stores-duckdb

Analyze the terminal output to locate any version of Llama index vector stores duckdb in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than 0.12.21), your application is affected.

Note: The pip show llama-index-vector-stores-duckdb command checks currently installed packages in your active Python environment.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-89: Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection'), where the product constructs all or part of an sql command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended sql command when it is sent to a downstream component. without sufficient removal or quoting of sql syntax in user-controllable inputs, the generated sql query can cause those inputs to be interpreted as sql instead of ordinary user data. In Llama index vector stores duckdb, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.

Source Advisory Statement

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).

CVE-2025-1750 Affected Llama index vector stores duckdb Versions

1 component(s)
Fixed Versions:
0.12.21
Product / Package Ecosystem Affected Versions Fixed Version
llama-index-vector-stores-duckdb
PyPI
≥ 0.12.19
< 0.12.21
0.12.21

References

Frequently Asked Questions

What is CVE-2025-1750?
CVE-2025-1750 is a security vulnerability in Llama index vector stores duckdb involving LlamaIndex DuckDBVectorStore vulnerable to SQL injection through ref_doc_id under CWE-89: Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection').
Which Llama index vector stores duckdb versions are affected?
Affected versions include releases prior to 0.12.21 across affected packages: llama-index-vector-stores-duckdb.
What version fixes CVE-2025-1750?
Upgrading to 0.12.21 (or the latest patched release for your respective branch) resolves the vulnerability.
Is llama-index-vector-stores-duckdb affected?
Yes, llama-index-vector-stores-duckdb is affected in releases prior to 0.12.21. Upgrade your dependency to 0.12.21 or later.
What is the CVSS score of CVE-2025-1750?
CVE-2025-1750 has a CVSS v3.1 base score of 9.8 (CRITICAL) with vector string CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
What CWE is associated with CVE-2025-1750?
CVE-2025-1750 is classified under CWE-89: Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection') (The product constructs all or part of an SQL command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended SQL command when it is sent to a downstream component. Without sufficient removal or quoting of SQL syntax in user-controllable inputs, the generated SQL query can cause those inputs to be interpreted as SQL instead of ordinary user data.).
How can I check PyPI dependencies for CVE-2025-1750?
Run the dependency tree command: 'pip show llama-index-vector-stores-duckdb'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.
Machine-readable OSV JSON OSV v1.5 Schema
Normalized schema output
{
  "schema_version" : "1.4.0",
  "id" : "GHSA-6mcc-q3mg-3qg6",
  "modified" : "2026-10-02T22:38:36Z",
  "published" : "2025-06-02T12:30:33Z",
  "aliases" : [ "CVE-2025-1750" ],
  "summary" : "LlamaIndex DuckDBVectorStore vulnerable to SQL injection through ref_doc_id",
  "details" : "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).",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "llama-index-vector-stores-duckdb"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0.12.19"
      }, {
        "fixed" : "0.12.21"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2025-1750"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/run-llama/llama_index/commit/369a2942df2efcf6b74461c45d20a0af1fbe4ae2"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/pypa/advisory-database/tree/main/vulns/llama-index/PYSEC-2025-245.yaml"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/run-llama/llama_index"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/run-llama/llama_index/releases/tag/v0.12.21"
  }, {
    "type" : "WEB",
    "url" : "https://huntr.com/bounties/e1302233-9180-4269-9047-1526247d2cd8"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-89" ],
    "severity" : "CRITICAL",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-10-02T22:38:36Z",
    "nvd_published_at" : "2025-06-02T10:15:20Z"
  }
}