CVE-2026-109228: SGLang through 0.5.21 Resource Budget Bypass via GLM-V Video Parameters
Noroxi assessment
Priority: Monitor (action score 34/100)
- The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
- Probability of exploitation in the next 30 days: 0.49% (FIRST EPSS).
- Anyone who can reach it over the internet can trigger it. No account or password is required. No user action is required. No special conditions are required; it is repeatable.
- According to CISA the attack is automatable: targets can be found by mass scanning.
- According to the record, no fixed version is available yet.
Low priority for now. Update when a fix is released; follow the vendor's advisory.
Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it
Primary sources: NVD · CVE.org · FIRST EPSS
SGLang through 0.5.21 contains a resource budget bypass vulnerability that allows remote attackers to override GLM-V video processing limits by supplying fps, max_frames, max_tokens_per_frame and max_image_tokens in the video_url object. Attackers can set these values arbitrarily high so glm4v.py decodes every frame of high-resolution video at full size, exhausting worker memory and denying service.
- Published
- Oct 12, 2026
- Updated
- Oct 14, 2026
- EPSS
- 0.4% · 42th percentile
- CWE
- CWE-770
Report tools
Action score
34
Low priority for now.
- CVSS
- 34 / 40 · 8.7 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.4%
CISA SSVC decision
- Exploitation
- none
- Automatable
- yes
- Technical impact
- partial
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- —
- CNA · VulnCheck
- 8.7
- NVD has not scored this yet; the score shown is the CNA’s.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.
Get told when this record changes
- Not in KEV: no record of exploitation in the wild
- No public exploit code on record
- No fixed version yet
If any of these changes, we'll tell you in the daily email digest.
Is your version affected? Check itNoroxi analysis
What does it mean in your environment?
The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.
We use this product, ask for helpAffected systems
Is your version affected?
Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.
—
Versions reported by the vendor
Affected version ranges reported by the assigning authority (VulnCheck). Independent of NVD's CPE analysis and usually ahead of it.
sgl-project sglang
- up to and including 0.5.21affected · semver
Same product
sgl-project: all recordsOther highest-scoring records for the same primary product.
- CVE-2026-111391SGLang 0.5.10 through 0.5.22 Code Injection via Debug Dumper Filter36Monitor
- CVE-2026-92972SGLang through 0.5.19 Unauthenticated Route Poisoning via PUT endpoint35Monitor
- CVE-2026-109229SGLang through 0.5.21 Decompression Bomb DoS via NanoNemotronVLImageProcessor34Monitor
Published before and after this one in the same product
- ← EarlierCVE-2026-109226Oct 12, 2026 · SGLang through 0.5.21 Audio Decompression Amplification via load_audio34Monitor
- ← EarlierCVE-2026-109227Oct 12, 2026 · SGLang through 0.5.21 Memory Exhaustion DoS via Qwen-VL Video Preprocessing34Monitor
- Later →CVE-2026-110807Oct 14, 2026 · sgl-project SGLang generate Endpoint io_struct.py denial of service8Monitor
Remediation
Which version to upgrade to
Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.
No fix version is recorded for this entry. Check the references for vendor advisories.
Exploit status
No known public exploit
No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.
Research context
For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.
Timeline
From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.
No dated events beyond publication.
FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).
Credits
All researchersFinders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.
- Jiapeng Lifinder
- Jiajia Liufinder
- Jiadai Wangfinder
Variant candidates
Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.
- CVE-2026-1092250 days apartSGLang through 0.5.21 Memory Exhaustion DoS via /v1/audio/transcriptions Upload34Monitor
- CVE-2026-1092270 days apartSGLang through 0.5.21 Memory Exhaustion DoS via Qwen-VL Video Preprocessing34Monitor
- CVE-2026-9368824 days apartSGLang through 0.5.19 Unbounded Memory Allocation via bootstrap_room34Monitor
- CVE-2026-9383824 days apartSGLang through 0.5.20 Unbounded Memory Allocation via STAGING_REQ chunk_idx32Monitor
- CVE-2026-1122697 days apartSGLang through 0.5.22 Memory Exhaustion via Unauthenticated Mooncake Decode Registrations28Monitor
- CVE-2026-1122707 days apartSGLang through 0.5.22 Memory Exhaustion via Mooncake STAGING_RSP chunk_idx28Monitor
Not on record for this CVE: patch commit or PR link · public bounty program.
Technical details
Attack conditions
- Anyone who can reach it over the internet can trigger it.
- No account or password is required.
- No user action is required.
- No special conditions are required; it is repeatable.
If successful
- Confidentiality
- Integrity
- Availability
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- None
- User interaction
- None
- Scope
- X
Weakness class (CWE)
CWE-770 · Allocation of Resources Without Limits or ThrottlingCVSS vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/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
nvd-secondary
Attack context
MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.
Attack patterns (CAPEC)
- FloodingCAPEC-125likelihood: High · Medium
- Excessive AllocationCAPEC-130likelihood: Medium · Medium
- XML Ping of the DeathCAPEC-147likelihood: Low · Medium
- Exponential Data ExpansionCAPEC-197likelihood: High · Medium
- Serialized Data Parameter BlowupCAPEC-229likelihood: High · High
- Serialized Data with Nested PayloadsCAPEC-230likelihood: Medium · High
- Oversized Serialized Data PayloadsCAPEC-231likelihood: Medium · High
- HTTP DoSCAPEC-469Low
ATT&CK techniques
- Network Denial of Service:Direct Network FloodT1498.001
- Network Denial of Service:Reflection AmplificationT1498.002
- Endpoint Denial of ServiceT1499
- Endpoint Denial of Service: OS Exhaustion FloodT1499.001
- Endpoint Denial of Service:Service Exhaustion FloodT1499.002
- Endpoint Denial of Service:Application Exhaustion FloodT1499.003
Change log (2)
- SSVC exploitation— → none
- Exploit maturity— → none
For records you follow, these changes also arrive as notifications. →
References
Show all references (6 more)Show less
- github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/entrypoints/openai/protocol.py#L592-L594
- github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/multimodal/processors/glm4v.py#L160-L167
- github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/multimodal/processors/glm4v.py#L400
- github.com/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/parser/conversation.py#L691
- github.com/sgl-project/sglang/issues/43705
- www.vulncheck.com/advisories/sglang-through-0.5.21-resource-budget-bypass-via-glm-v-video-parameters
Vendor advisories and official records. Exploit/PoC links are deliberately left out.