llmware-ai llmware up to 0.4.6 Collection Database Layer llmware/resources.py filter/lookup sql injection

Summaryinfo

A vulnerability identified as critical has been detected in llmware-ai llmware up to 0.4.6. Affected by this vulnerability is the function Library.block_lookup/Query.text_query_with_custom_filter of the file llmware/resources.py of the component Collection Database Layer. This manipulation of the argument filter/lookup causes sql injection. This vulnerability is tracked as CVE-2026-85689. The attack is possible to be carried out remotely. No exploit exists.

Detailsinfo

A vulnerability classified as critical was found in llmware-ai llmware up to 0.4.6. Affected by this vulnerability is the function Library.block_lookup/Query.text_query_with_custom_filter of the file llmware/resources.py of the component Collection Database Layer. The manipulation of the argument filter/lookup with an unknown input leads to a sql injection vulnerability. The CWE definition for the vulnerability is 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. As an impact it is known to affect confidentiality, integrity, and availability. The summary by CVE is:

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.

It is possible to read the advisory at github.com. This vulnerability is known as CVE-2026-85689 since 09/04/2026. The exploitation appears to be easy. The attack can be launched remotely. Technical details of the vulnerability are known, but there is no available exploit. The pricing for an exploit might be around USD $0-$5k at the moment (estimation calculated on 09/04/2026). The attack technique deployed by this issue is T1505 according to MITRE ATT&CK.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• llmware-ai

Name

• llmware

Version

• 0.4.0
• 0.4.1
• 0.4.2
• 0.4.3
• 0.4.4
• 0.4.5
• 0.4.6

Website

• Product: https://github.com/llmware-ai/llmware/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Discussion