CVE-2026-70640 json
llama.cpp b1886–b7445 Race Condition Use-After-Free via llama-android.cpp
published 3mo ago modified 3d ago also EUVD-2026-54280
- cvss
- 7.0
- 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 15%
- public exploits
- 0
- none known
Summary
llama.cpp builds b1886 through b7445 contain a race condition use-after-free vulnerability in the LLaMA-Android JNI wrapper where bench_1model() and free_1context() lack synchronization, allowing Thread A to operate on freed memory while Thread B concurrently frees the llama_context. Attackers can exploit this by performing heap spray with attacker-controlled data containing a fake vtable to hijack the vtable pointer at offset +0x30, causing llama_batch_allocr::clear() to dereference arbitrary memory and achieve remote code execution.
Patch / fix
- ggerganov llama.cpp b7446
- ggml llama.cpp b7446
- llama.cpp Debian 14 7593+dfsg-1
debian advisories DEBIAN-CVE-2026-70640
Is CVE-2026-70640 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
- none
- Automatable
- no
- Technical impact
- total
- Assessed
- 3mo ago
Exploit prediction
0.24% chance of exploitation in the next 30 days, higher than 15% of all scored CVEs (FIRST EPSS, 2026-11-11).
Exploits and checks
- vulncheck.com https://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-race-condition-use-after-free-via-llama-android-cpp referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 7.3 | CVSS:4.0/AV:L/AC:H/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N |
| CNA | 3.1 | 7.0 | CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H |
| CNA | 4.0 | 7.3 | CVSS:4.0/AV:L/AC:H/AT:N/PR:N/UI:P/VC:H/VI:H/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 |
Affected products
- ggml-org llama.cpp
Classification
References
-
github.com
/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388
patch
-
github.com
/ggml-org/llama.cpp/releases/tag/b7446
release-notes, patch, vendor-advisory
-
github.com
/Vladimir-tokarev-cyera/llama-cpp-security-patches
related, patch, third-party-advisory
-
vulncheck.com
/advisories/llama-cpp-b1886-b7445-race-condition-use-after-free-via-llama-android-cpp
third-party-advisory, exploit
Sources
- CVE List CVE-2026-70640
- NVD CVE-2026-70640
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.