CVE-2026-70640
Raw vector
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:XSummary
CVE-2026-70640 is a high-severity Race Condition (CWE-362) vulnerability. Its CVSS base score is 7.3 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Endpoint Denial of Service (T1499); ranked at the 6th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as NLP and Transformers.
The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SA-15 (Development Process, Standards, and Tools) — see the control section below for these in your framework.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-54280
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- NLP and Transformers
- Risk Domain
- N/A
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: llama.cpp, llama
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V10.4.2V10.4.5V15.1.3V15.4.1
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation (including static analysis) directly finds null-dereference bugs before deployment.
Documented development standards and tools can enforce null-safety rules and safe pointer usage.
Engineering principles can mandate defensive coding such as explicit null checks before dereference.
Maintaining separate execution domains for each process structurally eliminates unintended concurrent access to the same shared resources.
Preventing unintended information transfer through shared system resources directly addresses the improper concurrent modification that defines a race condition.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure SDLC practices directly require proper synchronization primitives and concurrency testing that prevent race conditions.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing can detect race conditions, but does not prevent them at design or coding time.
Secure SDLC mandates concurrency controls and synchronization primitives that directly prevent race conditions.
Application security requirements can specify thread-safety and locking rules, but do not prescribe implementation details.
Secure architecture principles require proper synchronization and resource isolation, addressing the root cause of CWE-362.
Secure coding standards explicitly forbid unsafe concurrent access patterns and mandate atomic operations or locks.
Change management reduces introduction of concurrency bugs during updates, yet does not address the weakness itself.