CVE-2026-63764
Unauthenticated SSRF in lmdeploy allows access to internal services and cloud metadata via image_url redirects.
Is CVE-2026-63764 being exploited?
Not confirmed. CVE-2026-63764 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 0.39% probability of exploitation in the next 30 days.
How severe is CVE-2026-63764?
CVE-2026-63764 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-2026-63764?
Yes. A fix has been recorded for CVE-2026-63764. The vendor advisory is the authority on the exact fixed version — apply it from there rather than from a summary.
What does CVE-2026-63764 affect?
CVE-2026-63764 affects lmdeploy OpenAI-compatible API server, chat completions endpoint (/v1/chat/completions), deployments that accept image_url and follow redirects, cloud metadata services (AWS/GCP instance metadata). Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2026-63764?
Restrict/validate redirects, block metadata access, enforce egress controls, update lmdeploy when patched.
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
Unauthenticated SSRF lets attackers reach internal services and cloud metadata (instance credentials), enabling data theft and cloud account compromise.
Immediate action required
- affected<= 0.14.0
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.