{"description":"Trending threats, MITRE ATT\u0026CK coverage, and detection metadata. Fed continuously.","feed_url":"https://feed.craftedsignal.io/products/llama.cpp-b1886-b7445/feed.json","home_page_url":"https://feed.craftedsignal.io/","items":[{"_cs_actors":[],"_cs_cpes":[],"_cs_cves":[{"cvss":7,"id":"CVE-2026-70640"}],"_cs_exploited":false,"_cs_has_poc":false,"_cs_poc_references":[],"_cs_products":["llama.cpp (b1886-b7445)"],"_cs_severities":["high"],"_cs_tags":[],"_cs_type":"advisory","_cs_vendors":[],"content_html":"\u003cp\u003eCVE-2026-70640 is a high-severity race condition vulnerability identified in the LLaMA-Android JNI wrapper of llama.cpp (builds b1886 through b7445). The flaw originates from insufficient synchronization between the bench_1model() and free_1context() functions. This missing synchronization allows a race condition where one thread can continue to operate on memory that has been freed by another thread during a concurrent call to free the llama_context.\u003c/p\u003e\n\u003cp\u003eAn attacker can exploit this condition by performing a heap spray to plant malicious data, including a forged vtable, into the heap memory. By targeting the vtable pointer at offset +0x30, the attacker can hijack execution flow when llama_batch_allocr::clear() is subsequently called. This results in the application dereferencing an attacker-controlled pointer, which may facilitate arbitrary code execution within the context of the Android application. Defenders should prioritize updating llama.cpp to a version beyond b7445 to mitigate this risk.\u003c/p\u003e\n\u003ch2 id=\"impact\"\u003eImpact\u003c/h2\u003e\n\u003cp\u003eThe vulnerability poses a significant risk to Android applications integrating the vulnerable llama.cpp builds. Successful exploitation could allow an attacker to achieve remote code execution on the host device, leading to full application compromise, unauthorized access to local user data, or further escalation of privileges within the Android environment.\u003c/p\u003e\n\u003ch2 id=\"recommendation\"\u003eRecommendation\u003c/h2\u003e\n\u003cul\u003e\n\u003cli\u003eUpdate all Android applications utilizing llama.cpp builds between b1886 and b7445 to a patched version immediately.\u003c/li\u003e\n\u003cli\u003eReview crash logs for Android applications for recurring segmentation faults or memory access violations involving the llama.cpp JNI wrapper, which may indicate attempted exploitation.\u003c/li\u003e\n\u003cli\u003eImplement memory safety checks and sanitize JNI boundary inputs in custom Android native wrappers to reduce the likelihood of memory-related vulnerabilities.\u003c/li\u003e\n\u003c/ul\u003e\n","date_modified":"2026-08-07T01:30:13Z","date_published":"2026-08-07T01:30:13Z","id":"https://feed.craftedsignal.io/briefs/2026-08-06-cve-2026-70640/","summary":"A race condition in the llama.cpp Android JNI wrapper allows attackers to trigger a use-after-free vulnerability, potentially leading to remote code execution through vtable pointer hijacking.","title":"CVE-2026-70640: Race Condition Use-After-Free in llama.cpp Android JNI Wrapper","url":"https://feed.craftedsignal.io/briefs/2026-08-06-cve-2026-70640/"},{"_cs_actors":[],"_cs_cpes":[],"_cs_cves":[{"cvss":8.1,"id":"CVE-2026-43629"}],"_cs_exploited":false,"_cs_has_poc":false,"_cs_poc_references":[],"_cs_products":["llama.cpp (b4882-b9058)","llama.cpp (b1886-b7445)","llama.cpp"],"_cs_severities":["high"],"_cs_tags":[],"_cs_type":"advisory","_cs_vendors":["ggerganov"],"content_html":"\u003cp\u003eThe llama.cpp project is affected by a heap buffer overflow vulnerability, identified as CVE-2026-43629, impacting builds from b4882 through b9058. The issue resides in the state_read_data() function, which is responsible for restoring the Key-Value (KV) cache state. During this process, the application performs size calculations for memory allocation without sufficient overflow checks. Specifically, the multiplication of the cell_count can result in an integer overflow, leading to an undersized tensor buffer allocation. An attacker who can write files to the configured slot_save_path directory can provide a crafted state file to trigger this overflow, writing arbitrary data beyond the allocated buffer boundaries. This allows for heap metadata corruption, model weight tampering, or arbitrary code execution through the overwriting of function pointers in memory.\u003c/p\u003e\n\u003ch2 id=\"impact\"\u003eImpact\u003c/h2\u003e\n\u003cp\u003eSuccessful exploitation of this vulnerability in environments utilizing llama.cpp for model inference allows local attackers with filesystem access to the application's storage paths to achieve code execution under the security context of the llama.cpp process. This poses a significant risk to servers hosting local LLM inference services where users or secondary processes have permissions to drop files into the llama.cpp working directory.\u003c/p\u003e\n\u003ch2 id=\"recommendation\"\u003eRecommendation\u003c/h2\u003e\n\u003col\u003e\n\u003cli\u003eUpgrade all llama.cpp installations currently running builds between b4882 and b9058 to build b9059 or later immediately.\u003c/li\u003e\n\u003cli\u003eRestrict write access to the directory designated for slot_save_path to only authorized users or service accounts to prevent the placement of malicious state files.\u003c/li\u003e\n\u003cli\u003eAudit filesystem permissions for all directories used by llama.cpp to ensure least privilege is applied to input/output paths.\u003c/li\u003e\n\u003c/ol\u003e\n","date_modified":"2026-08-07T01:30:06Z","date_published":"2026-08-06T23:30:22Z","id":"https://feed.craftedsignal.io/briefs/2026-08-llama-cpp-heap-overflow/","summary":"A heap buffer overflow vulnerability in llama.cpp builds b4882 through b9058 allows attackers with write access to the slot_save_path directory to achieve arbitrary code execution via malicious KV cache state files.","title":"Heap Buffer Overflow in llama.cpp KV Cache Restoration","url":"https://feed.craftedsignal.io/briefs/2026-08-llama-cpp-heap-overflow/"}],"language":"en","title":"CraftedSignal Threat Feed - Llama.cpp (B1886-B7445)","version":"https://jsonfeed.org/version/1.1"}