CVE-2026-111392

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.

CVSS v3 4.8 MEDIUM

4.8^/10

CVSS v3 : MEDIUM

Vector :

Exploitability : 2.2 / Impact : 2.5

Attack Vector NETWORK

Attack Complexity HIGH

Privileges Required NONE

User Interaction NONE

Confidentiality Impact LOW

Integrity Impact LOW

Availability Impact NONE

Scope UNCHANGED

References

Link	Resource
https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/managers/io_struct.py#L205-L215
https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/managers/tokenizer_manager.py#L1183-L1215
https://github.com/sgl-project/sglang/issues/44641
https://github.com/sgl-project/sglang/pull/44653
https://www.vulncheck.com/advisories/sglang-through-0.5.21-kv-cache-poisoning-via-mm-hashes-in-generate
https://github.com/sgl-project/sglang/issues/44641

Configurations

No configuration.

History

16 Oct 2026, 20:17

Type	Values Removed	Values Added
References	~~() https://github.com/sgl-project/sglang/issues/44641 -~~	() https://github.com/sgl-project/sglang/issues/44641 -

16 Oct 2026, 18:17

Type	Values Removed	Values Added
New CVE

Information

Published : 2026-10-16 18:17

Updated : 2026-10-16 20:17

NVD link : CVE-2026-111392

Mitre link : CVE-2026-111392

CVE.ORG link : CVE-2026-111392

JSON object : View

Products Affected

No product.

CWE

CWE-345

Insufficient Verification of Data Authenticity

{"id": "CVE-2026-111392", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-111392", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-10-16T19:24:20.694655Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 4.8, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:N", "integrityImpact": "LOW", "userInteraction": "NONE", "attackComplexity": "HIGH", "availabilityImpact": "NONE", "privilegesRequired": "NONE", "confidentialityImpact": "LOW"}, "impactScore": 2.5, "exploitabilityScore": 2.2}], "cvssMetricV40": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 6.3, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:L/VI:L/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", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "NONE", "attackComplexity": "HIGH", "attackRequirements": "PRESENT", "privilegesRequired": "NONE", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "LOW", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "NONE", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "LOW", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "affected": [{"source": "disclosure@vulncheck.com", "affectedData": [{"repo": "https://github.com/sgl-project/sglang", "vendor": "sgl-project", "product": "sglang", "versions": [{"status": "affected", "version": "0.5.13", "versionType": "custom", "lessThanOrEqual": "0.5.21"}], "packageURL": "pkg:github/sgl-project/sglang", "defaultStatus": "unaffected"}]}], "published": "2026-10-16T18:17:38.950", "references": [{"url": "https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/managers/io_struct.py#L205-L215", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/managers/tokenizer_manager.py#L1183-L1215", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/sgl-project/sglang/issues/44641", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/sgl-project/sglang/pull/44653", "source": "disclosure@vulncheck.com"}, {"url": "https://www.vulncheck.com/advisories/sglang-through-0.5.21-kv-cache-poisoning-via-mm-hashes-in-generate", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/sgl-project/sglang/issues/44641", "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"}], "vulnStatus": "Deferred", "weaknesses": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "description": [{"lang": "en", "value": "CWE-345"}]}], "descriptions": [{"lang": "en", "value": "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."}], "lastModified": "2026-10-16T20:17:20.370", "sourceIdentifier": "disclosure@vulncheck.com"}