# CVE-2026-49948: Mem0 missing authorization in POST /configure endpoint

Source: https://junglewise.ai/threats/cve-2026-49948-mem0-missing-authorization-in-post-configure-endpoint  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-06-09. Updated: 2026-06-09  
License: CC BY 4.0 with a link back

CVE-2026-49948 · Severity: high · CVSS 8.1 · Published 2026-06-09

Mem0 is a memory layer for AI applications that stores and manages context for LLMs. A security flaw in its self-hosted server allows any user with a valid API key to change the system's global configuration. An attacker could use this to redirect all AI traffic to their own server, allowing them to steal sensitive conversation data, prompts, and personal information from every user on the platform.

## Quick answers

**Is CVE-2026-49948 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-49948 being exploited in the wild.

**How severe is CVE-2026-49948?** High severity, with a CVSS score of 8.1, published 9 June 2026.

**Which products and versions are affected?** mem0ai Mem0 through 0.2.8.

**Is there a fix for CVE-2026-49948?** A patch was published on 2026-06-05: Fixed in commit ae7f406 and PR #5360. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-49948 attacked?** It is attacked over the network, in a hosted service.

**Am I affected by CVE-2026-49948?** Check whether anything you run is named in the advisory. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

A missing authorization check in the 'POST /configure' endpoint of the Mem0 self-hosted server allows any authenticated user (via JWT or X-API-Key) to modify global LLM provider and embedder configurations. While the server implements a 'verify_auth' dependency, it fails to validate the user's role, allowing non-admin API key holders to execute administrative configuration changes. An attacker can redirect all LLM and embedding traffic to an external malicious endpoint, enabling full data exfiltration of prompts and memories. The malicious configuration is persisted to the PostgreSQL database and survives server restarts. This was fixed in commit ae7f406 by implementing role-based access control.

## Affected products

- mem0ai Mem0 through 0.2.8

## Timeline

- 2026-05-12: disclosed: Vulnerability discovered and reported via GitHub issues.
- 2026-06-05: patched: Fixed in commit ae7f406 and PR #5360.
- 2026-06-09: advisory: CVE-2026-49948 published.

## References

- [https://github.com/mem0ai/mem0/commit/ae7f4062652df1376990221101d1adbb0819c973](https://github.com/mem0ai/mem0/commit/ae7f4062652df1376990221101d1adbb0819c973)
- [https://github.com/mem0ai/mem0/issues/5127](https://github.com/mem0ai/mem0/issues/5127)
- [https://github.com/mem0ai/mem0/issues/5384](https://github.com/mem0ai/mem0/issues/5384)
- [https://github.com/mem0ai/mem0/pull/5360](https://github.com/mem0ai/mem0/pull/5360)
- [https://www.vulncheck.com/advisories/mem0-missing-authorization-via-post-configure-endpoint](https://www.vulncheck.com/advisories/mem0-missing-authorization-via-post-configure-endpoint)