CVE-2026-111392 json
SGLang through 0.5.21 KV Cache Poisoning via mm_hashes in /generate
published 24d ago modified 24d ago also EUVD-2026-103024
- cvss
- 4.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.2%
- EPSS 0.2% chance of exploitation in 30 days, percentile 10%
- public exploits
- 0
- none known
Summary
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.
Patch / fix
- github.com/sgl-project/sglang#44653 pull request
Is CVE-2026-111392 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerCISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- partial
- Assessed
- 24d ago
Exploit prediction
0.21% chance of exploitation in the next 30 days, higher than 10% of all scored CVEs (FIRST EPSS, 2026-11-09).
Exploits and checks
- github.com https://github.com/sgl-project/sglang/issues/44641 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 6.3 | 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 |
| CNA | 3.1 | 4.8 | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:N |
| CNA | 4.0 | 6.3 | 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 |
Affected products
- sgl-project sglang
Classification
- Weakness
-
- CWE-345 Insufficient Verification of Data Authenticity
References
-
github.com
/sgl-project/sglang/pull/44653
patch, issue-tracking
-
github.com
/sgl-project/sglang/issues/44641
issue-tracking, exploit
-
github.com
/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/managers/tokenizer_manager.py#L1183-L1215
technical-description
-
github.com
/sgl-project/sglang/blob/v0.5.21/python/sglang/srt/managers/io_struct.py#L205-L215
technical-description
-
vulncheck.com
/advisories/sglang-through-0.5.21-kv-cache-poisoning-via-mm-hashes-in-generate
third-party-advisory
Sources
- CVE List CVE-2026-111392
- NVD CVE-2026-111392
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.