CVE-2026-127222: SGLang 0.5.23 Missing Authorization via load_lora_adapter_from_tensors
SGLang through 0.5.23, fixed in commit 7b5fb39, contains a missing authorization vulnerability in the POST /loadloraadapterfromtensors HTTP endpoint, which lacks the @authlevel(AuthLevel.ADMINOPTIONAL) decorator applied to its sibling admin endpoints, allowing unauthenticated network-reachable attackers to invoke it without an API key. Attackers can load a LoRA adapter from attacker-supplied serialized tensors to manipulate the served model, and when combined with a separately documented deserialization bypass, achieve unauthenticated remote code execution as root.
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade to a fixed release to a version that resolves this vulnerability.
Patch 7b5fb39