Database/AI/ML frameworks & serving
Ollama (quantization engine): Unauthenticated remote information disclosure — reads and exfiltrates model data
CVE-2026-5757AI/ML frameworks & servingcurated
Impact
Unauthenticated remote information disclosure — reads and exfiltrates model data
Who can reach it
Unauthenticated network to the quantization endpoint
What to do
Upgrade; direct cross-tenant model-weight exposure if Ollama is shared
References
This entry is curated: imported from vendor advisories with machine assistance, not yet individually verified. Confirm against your vendor's advisory before acting, and report anything wrong.