CriticalVulnerabilityLLM-specific

CVE-2026-59706: mem0 unauthenticated config API exposes LLM API keys and enables SSRF

Source: NVD(opens in a new tab)
Identifier: CVE-2026-59706
Published: July 7, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.4%

Summary

CVE-2026-59706 affects mem0 and describes unauthenticated config API endpoints. An unauthenticated attacker can retrieve stored secrets such as OpenAI API keys in plaintext via GET /api/v1/config/, or trigger server-side request forgery by setting ollama_base_url to internal addresses such as cloud IMDS through PUT /api/v1/config/mem0/llm. VulnCheck rates it CVSS 4.0 9.2 CRITICAL, while NVD has not yet provided an assessment.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 9.3(critical)
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N
Attack vector: network
Attack complexity: low
Privileges required: none
User interaction: none
EPSS: 0.4%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on October 11, 2026.
Disclosure date: July 7, 2026

Weaknesses and techniques

Weakness (CWE): CWE-306
Attack pattern (CAPEC): CAPEC-115
AI threat technique (MITRE ATLAS): AML.T0010

Affected

Vendors: OpenAI

Classification

Attack type: Data extraction,
Supply chain
Attack sophistication: Trivial
AI component targeted: API
Impact: Confidentiality,
Integrity
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-59706

First tracked: July 7, 2026 at 08:07 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Summary

Mitigation

Related items