Browse / RAG and Vector Store Weaknesses / CVE-2026-115324
mem0ai Databricks vector store vulnerable to SQL injection
- Class
- RAG and Vector Store Weaknesses (filed by a model that read the advisory)
- Technique
- SQL and query injection
- Also involves
- Agent Context and Memory Poisoning
- Affected
- mem0ai (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 0.3% chance of exploitation in 30 days
How it works, in short
Stored memory text or metadata reaches unescaped string interpolation in the Databricks vector store's insert and update statements, so attacker-chosen SQL runs on the warehouse. (Our summary, written by a model. The source text is below.)
Details
mem0 0.1.117 before 1.0.8 contains an sql injection vulnerability in mem0/vector_stores/databricks.py that allows attackers to inject SQL by influencing stored memory content. Attackers can supply crafted memory text, metadata, or message names that reach unescaped insert() and update() string interpolation to execute injected SQL on the configured Databricks SQL warehouse.
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-115324
- https://github.com/mem0ai/mem0/issues/4073
- https://github.com/mem0ai/mem0/pull/4558
- https://github.com/mem0ai/mem0/commit/a2ffca32660537b7b304305f36774ae2a13452cb
- https://github.com/mem0ai/mem0
- https://github.com/mem0ai/mem0/blob/v1.0.7/mem0/vector_stores/databricks.py
- https://github.com/mem0ai/mem0/releases/tag/v1.0.8
- https://www.vulncheck.com/advisories/mem0-0.1.117-before-1.0.8-sql-injection-via-databricks-vector-store
Source: GitHub Advisory Database, used under CC BY 4.0.