LLM frameworks · Mem0 (open source)
Mem0
Open-source memory layer that gives AI agents and apps persistent, per-user memory, with Python and TypeScript SDKs.
2Advisories
0critical
1high
1medium
2026-10-26Latest
Timeline · advisories per quarter
22026 Q4
Named in sources
Reported for Mem0
01. CVE-2026-115324: Mem0's Databricks vector store built SQL from memory text, so crafted memories could inject SQLMem0 (mem0ai) 0.1.117 to before 1.0.8 built INSERT and UPDATE statements in its Databricks vector store by pasting memory text, metadata and message names straight into SQL. Anyone who can influence what gets stored as a memory, including through a chat with your agent, could run injected SQL on your Databricks SQL warehouse. Fixed in mem0ai 1.0.8. Mem0 2026-10-22 02. CVE-2026-116575: Mem0 could mix up two users' conversation history, leaking one tenant's messages to anotherMem0's Python and TypeScript SDKs built the key for each session's recent messages by joining user_id, agent_id and run_id with unescaped & and = characters. A caller who controls only their own run_id or agent_id could craft a value that produces another tenant's key, then read that tenant's recent raw messages and write into their history. Fixed in Python SDK 2.0.18 and TypeScript SDK 3.1.6. Mem0 2026-10-26
Mem0 2026-10-22 02. CVE-2026-116575: Mem0 could mix up two users' conversation history, leaking one tenant's messages to anotherMem0's Python and TypeScript SDKs built the key for each session's recent messages by joining user_id, agent_id and run_id with unescaped & and = characters. A caller who controls only their own run_id or agent_id could craft a value that produces another tenant's key, then read that tenant's recent raw messages and write into their history. Fixed in Python SDK 2.0.18 and TypeScript SDK 3.1.6. Mem0 2026-10-26