sgl-project SGLang up to 0.5.21 Multimodal Prefix-Cache Key generate mm_hashes information disclosure

Summaryinfo

A vulnerability was found in sgl-project SGLang up to 0.5.21. It has been classified as problematic. This affects the function Generate of the component Multimodal Prefix-Cache Key. This manipulation of the argument mm_hashes causes information disclosure. This vulnerability appears as CVE-2026-111392. The attack may be initiated remotely. There is no available exploit.

Detailsinfo

A vulnerability classified as problematic was found in sgl-project SGLang up to 0.5.21. Affected by this vulnerability is the function generate of the component Multimodal Prefix-Cache Key. The manipulation of the argument mm_hashes with an unknown input leads to a information disclosure vulnerability. The CWE definition for the vulnerability is CWE-200. The product exposes sensitive information to an actor that is not explicitly authorized to have access to that information. As an impact it is known to affect confidentiality. The summary by CVE is:

SGLang through 0.5.21 trusts caller-supplied mm_hashes values as the multimodal prefix-cache key, allowing remote attackers to poison cached KV entries across requests. Attackers can send a different image under a known or predicted hash via /generate to disclose another request's image content or corrupt victims' responses.

It is possible to read the advisory at github.com. This vulnerability is known as CVE-2026-111392 since 10/15/2026. The exploitation appears to be easy. The attack can be launched remotely. The exploitation doesn't need any form of authentication. Technical details of the vulnerability are known, but there is no available exploit. The pricing for an exploit might be around USD $0-$5k at the moment (estimation calculated on 10/16/2026). The attack technique deployed by this issue is T1592 according to MITRE ATT&CK.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Productinfo

Type

• Project Management Software

Vendor

• sgl-project

Name

• SGLang

Version

• 0.5.0
• 0.5.1
• 0.5.2
• 0.5.3
• 0.5.4
• 0.5.5
• 0.5.6
• 0.5.7
• 0.5.8
• 0.5.9
• 0.5.10
• 0.5.11
• 0.5.12
• 0.5.13
• 0.5.14
• 0.5.15
• 0.5.16
• 0.5.17
• 0.5.18
• 0.5.19
• 0.5.20
• 0.5.21

Website

• Product: https://github.com/sgl-project/sglang/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Discussion