Database/AI/ML frameworks & serving
vLLM (`load_from_url_async`): Bypass of the CVE-2026-24779 SSRF fix
CVSS 7.1CVE-2026-25960AI/ML frameworks & servingcurated
Impact
Bypass of the CVE-2026-24779 SSRF fix
Who can reach it
Unauthenticated request
What to do
Upgrade past 0.15.1. Third SSRF in the same connector — network-layer egress control is the only durable fix
References
Related entries
- LangSmith SDK: pulling a public Hub prompt deserializes attacker-controlled LangChain objectsCVE-2026-45134 · LangSmith SDK (pull_prompt / pullPrompt manifest deserialization)High
- picklescan: `scan_pytorch` bypass via forged magic numbersCVE-2026-53875 · picklescanHigh
- NVIDIA Megatron-LM: hash collisions in the inference cache let one request's data reach anotherCVE-2026-65104 · NVIDIA Megatron-LM (inference request cache)High
- torchvision (GIF decoder): Out-of-bounds heap read in `read_from_tensor` GIF decodeCVE-2026-65918 · torchvision (GIF decoder)High
- MLflow: model version creation reads another user's run artifacts without READ permissionCVE-2026-69148 · MLflow tracking server (CreateModelVersion source run/model validation)High
- MLflow AI Gateway: unvalidated api_base in gateway secrets turns the proxy endpoint into an authenticated SSRFCVE-2026-71211 · MLflow AI Gateway (gateway secret auth_config.api_base, raw_proxy endpoint)High
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.