CVE-2026-85689
Received Received - Intake

SQL Injection in llmware 0.4.6 Collection Database

Publication date: 2026-09-04

Last updated on: 2026-09-04

Assigner: VulnCheck

Description
llmware 0.4.6 contains an SQL injection vulnerability in the collection-database layer (llmware/resources.py) where filter and lookup values are directly string-interpolated into SQL WHERE clauses without parameterization or escaping, in both the SQLite and PostgreSQL backends. The filter validator only checks keys against an allow-list and never sanitizes values. Attacker-controlled filter values reaching the public API via Library.block_lookup and Query.text_query_with_custom_filter / text_query_by_author_or_speaker can neutralize the intended filter to disclose rows the caller was scoped out of (cross-document/cross-collection disclosure); on PostgreSQL the flaw permits boolean- and UNION-based SQL injection.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-09-04
Last Modified
2026-09-04
Generated
2026-09-04
AI Q&A
2026-09-04
EPSS Evaluated
N/A
NVD
CVE-2026-85689
EUVD
EUVD-2026-71138

Affected Vendors & Products

Showing 2 associated CPEs
Vendor Product Version / Range
llmware llmware to 0.4.6 (inc)
llmware llmware 0.4.6

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-89 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.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

llmware 0.4.6 has an SQL injection flaw in its collection-database layer (llmware/resources.py). The issue occurs when filter and lookup values are directly inserted into SQL WHERE clauses without proper sanitization or parameterization. The filter validator only checks keys against an allow-list and does not sanitize values, allowing attacker-controlled inputs to bypass intended filters.

Detection Guidance

To detect this SQL injection vulnerability in llmware 0.4.6, inspect the application logs for suspicious SQL queries in the collection-database layer. Look for filter values that bypass intended access controls. Check for unusual UNION-based queries or boolean-based injections in PostgreSQL logs. Review API calls to Library.block_lookup and Query.text_query_with_custom_filter for malformed filter parameters.

Impact Analysis

This vulnerability could allow attackers to access unauthorized data by manipulating SQL queries. In SQLite, it may enable cross-document or cross-collection disclosure. In PostgreSQL, it permits more severe attacks like boolean-based or UNION-based SQL injection, potentially leading to data theft or manipulation.

Compliance Impact

This vulnerability could lead to unauthorized data access or disclosure, violating GDPR's data protection principles and HIPAA's security requirements for protected health information. Non-compliance may result in legal penalties, reputational damage, and loss of trust.

Mitigation Strategies

Immediately upgrade llmware to a patched version beyond 0.4.6. If upgrading is not possible, implement strict input validation for all filter parameters in the API. Use parameterized queries instead of string interpolation for SQL WHERE clauses. Restrict database user permissions to limit exposure. Monitor database logs for unusual query patterns.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-85689. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart