CVE-2026-127222 (GCVE-0-2026-127222)
Vulnerability from cvelistv5 – Published: 2026-11-18 20:28 – Updated: 2026-11-19 15:58 X_Open Source
VLAI
EPSS
VEX
Title
SGLang 0.5.23 Missing Authorization via load_lora_adapter_from_tensors
Summary
SGLang through 0.5.23, fixed in commit 7b5fb39, contains a missing authorization vulnerability in the POST /load_lora_adapter_from_tensors HTTP endpoint, which lacks the @auth_level(AuthLevel.ADMIN_OPTIONAL) 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.
Severity
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-11-19 15:51 UTC
CWE
- CWE-862 - Missing Authorization
Assigner
References
5 references
| URL | Tags |
|---|---|
| https://rahulkarne.com/#/cve/CVE-2026-127222 | technical-descriptionexploit |
| https://github.com/rahulreddykarne/CVE-2026-12722… | technical-descriptionexploit |
| https://github.com/sgl-project/sglang/pull/49896 | issue-trackingpatch |
| https://github.com/sgl-project/sglang/commit/7b5f… | issue-trackingpatch |
| https://www.vulncheck.com/advisories/sglang-missi… | third-party-advisory |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| sgl-project | sglang |
Affected:
0 , ≤ 0.5.23
(semver)
Unaffected: 7b5fb39bb952da5f6da3bb7fe73c671cf449b6fa (git) |
Date Public
2026-11-14 00:00
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-127222",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-11-19T15:51:22.982039Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-11-19T15:58:31.887Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"packageURL": "pkg:pypi/sglang",
"product": "sglang",
"repo": "https://github.com/sgl-project/sglang",
"vendor": "sgl-project",
"versions": [
{
"lessThanOrEqual": "0.5.23",
"status": "affected",
"version": "0",
"versionType": "semver"
},
{
"status": "unaffected",
"version": "7b5fb39bb952da5f6da3bb7fe73c671cf449b6fa",
"versionType": "git"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Rahul Karne"
}
],
"datePublic": "2026-11-14T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "SGLang through 0.5.23, fixed in commit 7b5fb39, contains a missing authorization vulnerability in the POST /load_lora_adapter_from_tensors HTTP endpoint, which lacks the @auth_level(AuthLevel.ADMIN_OPTIONAL) 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."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.7,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
},
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "NONE",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-862",
"description": "Missing Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-11-18T20:28:08.927Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "Researcher Blog",
"tags": [
"technical-description",
"exploit"
],
"url": "https://rahulkarne.com/#/cve/CVE-2026-127222"
},
{
"name": "Researcher GitHub Repo",
"tags": [
"technical-description",
"exploit"
],
"url": "https://github.com/rahulreddykarne/CVE-2026-127222-sglang"
},
{
"name": "Pull Request",
"tags": [
"issue-tracking",
"patch"
],
"url": "https://github.com/sgl-project/sglang/pull/49896"
},
{
"name": "Patch Commit",
"tags": [
"issue-tracking",
"patch"
],
"url": "https://github.com/sgl-project/sglang/commit/7b5fb39bb952da5f6da3bb7fe73c671cf449b6fa"
},
{
"name": "VulnCheck Advisory: SGLang 0.5.23 Missing Authorization via load_lora_adapter_from_tensors",
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/sglang-missing-authorization-via-load-lora-adapter-from-tensors"
}
],
"tags": [
"x_open-source"
],
"title": "SGLang 0.5.23 Missing Authorization via load_lora_adapter_from_tensors",
"x_generator": {
"engine": "vulncheck"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-127222",
"datePublished": "2026-11-18T20:28:08.927Z",
"dateReserved": "2026-11-12T16:30:10.904Z",
"dateUpdated": "2026-11-19T15:58:31.887Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-127222",
"date": "2026-11-22",
"epss": "0.00575",
"percentile": "0.484"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"defaultStatus": "unaffected",
"packageURL": "pkg:pypi/sglang",
"product": "sglang",
"repo": "https://github.com/sgl-project/sglang",
"vendor": "sgl-project",
"versions": [
{
"lessThanOrEqual": "0.5.23",
"status": "affected",
"version": "0",
"versionType": "semver"
},
{
"status": "unaffected",
"version": "7b5fb39bb952da5f6da3bb7fe73c671cf449b6fa",
"versionType": "git"
}
]
}
],
"source": "disclosure@vulncheck.com"
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "SGLang through 0.5.23, fixed in commit 7b5fb39, contains a missing authorization vulnerability in the POST /load_lora_adapter_from_tensors HTTP endpoint, which lacks the @auth_level(AuthLevel.ADMIN_OPTIONAL) 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."
}
],
"id": "CVE-2026-127222",
"lastModified": "2026-11-19T16:19:43.760",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "NONE",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N",
"version": "3.1"
},
"exploitabilityScore": 3.9,
"impactScore": 3.6,
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
],
"cvssMetricV40": [
{
"cvssData": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"availabilityRequirement": "NOT_DEFINED",
"baseScore": 8.7,
"baseSeverity": "HIGH",
"confidentialityRequirement": "NOT_DEFINED",
"exploitMaturity": "NOT_DEFINED",
"integrityRequirement": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-127222",
"options": [
{
"exploitation": "poc"
},
{
"automatable": "yes"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-11-19T15:51:22.982039Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-11-18T21:17:48.157",
"references": [
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/rahulreddykarne/CVE-2026-127222-sglang"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/sgl-project/sglang/commit/7b5fb39bb952da5f6da3bb7fe73c671cf449b6fa"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/sgl-project/sglang/pull/49896"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://rahulkarne.com/#/cve/CVE-2026-127222"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://www.vulncheck.com/advisories/sglang-missing-authorization-via-load-lora-adapter-from-tensors"
}
],
"sourceIdentifier": "disclosure@vulncheck.com",
"vulnStatus": "Deferred",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-862"
}
],
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
]
}
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-127222",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-11-19T15:51:22.982039Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-11-19T15:51:24.751Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"packageURL": "pkg:pypi/sglang",
"product": "sglang",
"repo": "https://github.com/sgl-project/sglang",
"vendor": "sgl-project",
"versions": [
{
"lessThanOrEqual": "0.5.23",
"status": "affected",
"version": "0",
"versionType": "semver"
},
{
"status": "unaffected",
"version": "7b5fb39bb952da5f6da3bb7fe73c671cf449b6fa",
"versionType": "git"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Rahul Karne"
}
],
"datePublic": "2026-11-14T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "SGLang through 0.5.23, fixed in commit 7b5fb39, contains a missing authorization vulnerability in the POST /load_lora_adapter_from_tensors HTTP endpoint, which lacks the @auth_level(AuthLevel.ADMIN_OPTIONAL) 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."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.7,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
},
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "NONE",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-862",
"description": "Missing Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-11-18T20:28:08.927Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "Researcher Blog",
"tags": [
"technical-description",
"exploit"
],
"url": "https://rahulkarne.com/#/cve/CVE-2026-127222"
},
{
"name": "Researcher GitHub Repo",
"tags": [
"technical-description",
"exploit"
],
"url": "https://github.com/rahulreddykarne/CVE-2026-127222-sglang"
},
{
"name": "Pull Request",
"tags": [
"issue-tracking",
"patch"
],
"url": "https://github.com/sgl-project/sglang/pull/49896"
},
{
"name": "Patch Commit",
"tags": [
"issue-tracking",
"patch"
],
"url": "https://github.com/sgl-project/sglang/commit/7b5fb39bb952da5f6da3bb7fe73c671cf449b6fa"
},
{
"name": "VulnCheck Advisory: SGLang 0.5.23 Missing Authorization via load_lora_adapter_from_tensors",
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/sglang-missing-authorization-via-load-lora-adapter-from-tensors"
}
],
"tags": [
"x_open-source"
],
"title": "SGLang 0.5.23 Missing Authorization via load_lora_adapter_from_tensors",
"x_generator": {
"engine": "vulncheck"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-127222",
"datePublished": "2026-11-18T20:28:08.927Z",
"dateReserved": "2026-11-12T16:30:10.904Z",
"dateUpdated": "2026-11-19T15:58:31.887Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Loading…
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.
Loading…