Severity by source
CVSS:4.0/AV:L/AC:H/AT:N/PR:L/UI:N/VC:N/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/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
Primary rating from NVD · only source for this CVE.
CVSS VectorNVD
CVSS:4.0/AV:L/AC:H/AT:N/PR:L/UI:N/VC:N/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/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
Lifecycle Timeline
3DescriptionCVE.org
A vulnerability was determined in sgl-project SGLang up to 0.5.11. Affected by this vulnerability is the function data_hash of the component Cache Handler. This manipulation causes denial of service. The attack is restricted to local execution. A high degree of complexity is needed for the attack. The exploitation appears to be difficult. The exploit has been publicly disclosed and may be utilized. The pull request to fix this issue awaits acceptance.
AnalysisAI
Hash collision weaknesses in SGLang's multimodal Cache Handler (all versions through 0.5.11) allow a local low-privilege attacker to craft multimodal tensor inputs that produce identical cache keys via truncated SHA256 digests, causing incorrect cache lookups or cache invalidation failures that disrupt LLM serving workflows. The CVSS 4.0 score of 1.1 reflects the strictly local attack vector and high exploitation complexity, limiting real-world impact primarily to multi-tenant inference deployments. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
Free forever · No credit card required
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | Local system access is required - this vulnerability cannot be exploited remotely (AV:L). … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | The CVSS 4.0 score of 1.1 (AV:L/AC:H/AT:N/PR:L/UI:N/VC:N/VI:L/VA:L with E:P) places this at the bottom of the severity scale. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | A local user on a shared SGLang multimodal inference server submits a crafted series of tensor inputs engineered to produce identical 8-byte-truncated SHA256 cache keys. Because tensor shape and dtype are not incorporated into the hash, two tensors with identical raw byte values but different shapes hash identically. … |
| Remediation | Upstream fix available via GitHub PR #22033 (https://github.com/sgl-project/sglang/pull/22033), which expands SHA256 truncation from 8 to 16 bytes across all hash functions, introduces shape and dtype boundary markers as structural metadata in tensor hash derivation, replaces Python's non-deterministic hash() in multimodal_cache.py with deterministic SHA256, and adds type-tagged serialization for nested list inputs to prevent cross-type collisions. … Detailed patch versions, workarounds, and compensating controls in full report. |
Threat intelligence, references, and detailed analysis are available after sign-in.
Share
External POC / Exploit Code
Leaving vuln.today
EUVD-2026-34185
GHSA-jrcc-j37m-v8fg