ZeroDay Findings
Sign inSign up

Findings

CVE-2026-32628

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting.

Published Mar 16, 2026 · updated Jun 17, 2026 · mintplexlabs anythingllm

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, a SQL injection vulnerability in the built-in SQL Agent plugin allows any user who can invoke the agent to execute arbitrary SQL commands on connected databases. The getTableSchemaSql() method in all three database connectors (MySQL, PostgreSQL, MSSQL) constructs SQL queries using direct string concatenation of the table_name parameter without sanitization or parameterization.

Code

The project this record applies to. Exploit listings stay in References.

Timeline

Detection, updates, and resolution for this record.

  1. Mar 16, 2026 · NIST NVD

    Detected

    AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, a SQL injection vulnerability in the built-in SQL Agent plugin allows any user who can invoke the agent to execute arbitrary SQL commands on connected databases. The getTableSchemaSql() method in all three database connectors (MySQL, PostgreSQL, MSSQL)

  2. Jun 17, 2026 · NIST NVD

    Updated

    AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, a SQL injection vulnerability in the built-in SQL Agent plugin allows any user who can invoke the agent to execute arbitrary SQL commands on connected databases. The getTableSchemaSql() method in all three database connectors (MySQL, PostgreSQL, MSSQL)

Affected

  • cpe mintplexlabs/anythingllmversion unspecified

Sources

  • CVE.orgVulnerability recordCVE-2026-32628

    Official CVE identifier

    cve.org
  • NIST NVDVulnerability recordCVE-2026-32628

    AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, a SQL injection vulnerability in the built-in SQL Agent plugin allows any user who can invoke the agent to execute arbitrary SQL comm

    nvd.nist.gov

References