CVE-2026-59706
Unauthenticated API exposes LLM API keys and enables SSRF to internal services.
Is CVE-2026-59706 being exploited?
Not confirmed. CVE-2026-59706 does not appear in CISA's Known Exploited Vulnerabilities catalog, which records only exploitation that has been observed and reported publicly. That is evidence of absence of a report, not evidence the flaw is unattacked. EPSS currently estimates a 0.44% probability of exploitation in the next 30 days.
How severe is CVE-2026-59706?
CVE-2026-59706 is rated Critical with a CVSS score of 9.2. Severity describes how bad exploitation would be, not how likely it is: pair it with exploitation evidence before deciding what to patch first.
Is there a patch for CVE-2026-59706?
Not known from our data. No patch reference has been recorded for CVE-2026-59706, which is not the same as no patch existing — a fix may have shipped without a tagged reference, or after this record was written. The vendor advisory is the only authority on whether a fix exists, and mitigations may be available regardless.
What does CVE-2026-59706 affect?
CVE-2026-59706 affects mem0 config API (unauthenticated), ollama_base_url parameter, Stored LLM/OpenAI API keys. Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2026-59706?
Disable/ firewall mem0 config API, rotate exposed keys, block IMDS egress, apply vendor patch when available.
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
Unauthenticated attackers can retrieve plaintext LLM/OpenAI API keys and perform SSRF (e.g., to cloud IMDS) enabling credential theft and internal access.
Immediate action required
- affected<= a3154d5
As published in the CVE Program record. A version outside these ranges is not a statement that it is unaffected — vendors sometimes understate a range, and distribution-backported builds carry upstream numbers that do not reflect what was patched into them.