Vulnerability · Published Sep 4, 2026 · Assigned by VulnCheck

CVE-2026-85689llmware 0.4.6 SQL Injection via unescaped filter values

Medium 6.5

In plain English

A medium-severity SQL injection in llmware from llmware-ai. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 37% of all known vulnerabilities).

Severity (CVSS 3.1)6.5Medium

Exploit odds (30 days)0.4%top 63.5% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected products (as reported)

Vendor	Product	Versions
llmware-ai	llmware	0 – through 0.4.6

Weakness: CWE-89 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

References

GitHub Issue #1304 issue-tracking
https://github.com/llmware-ai/llmware product
https://github.com/llmware-ai/llmware/blob/v0.4.6/llmware/resources.py technical-description
VulnCheck Advisory: llmware 0.4.6 SQL Injection via unescaped filter values third-party-advisory