Lucene search
+L

1054 matches found

Kitploit
Kitploit
•added 2026/11/16 11:33 p.m.•42 views

Google-Tensor-Chips

Google Tensor Chips — DarWINN NPU Access Direct-access tooling for the Google Tensor NPU DarWINN, reverse-engineered across two generations: Tensor G2 Pixel 7, codename Janeiro and Tensor G3 Pixel 8, codename Rio. Why this exists I was trying to get LLM inference running on the phone and wanted t...

6.1AI score
SaveExploits0References5
Kitploit
Kitploit
•added 2026/11/16 12:15 p.m.•38 views

CVE-2026-7020

CVE-2026-7020 Ollama arbitrary file read via tensor digest path traversal. Exfiltrates SSH host keys and any other file from a reachable Ollama host in three unauthenticated API calls. Writeup: Co-Researcher @gouldnicholas Usage python3 poc.py Tries all three SSH host key types with known sizes a...

6.3CVSS6.1AI score0.00908EPSS
SaveExploits2References1
Kitploit
Kitploit
•added 2026/11/16 11:00 a.m.•35 views

CVE-2026-34159-Vulnerability-Research-Analysis-Detection

CVE-2026-34159-Vulnerability-Research-Analysis-Detection Critical buffer validation bypass in deserializetensor llama.cpp b8492. Null tensor buffer skips bounds check, enabling unauthenticated arbitrary R/W via GRAPHCOMPUTE. ASLR bypass + RCE over TCP 50052. Contains: Technical analysis & exploit...

9.8CVSS7.9AI score0.01623EPSS
SaveExploits2
osv_cve
osv_cve
•added 2026/11/05 3:26 p.m.•15 views

CVE-2026-70659 stable-diffusion.cpp: Heap out-of-bounds write in the imatrix loader (`load_imatrix`) via a duplicate tensor name

stable-diffusion.cpp is a pure C/C++ library for running diffusion model Stable Diffusion, Flux, Wan, Qwen Image, Z-Image, and more inference. From master-742-1a13107 until master-763-4fcc6fe, IMatrixCollector::loadimatrix in src/runtime/imatrix.cpp reuses the values and counts vectors for entrie...

7.8CVSS6AI score
SaveExploits0References6
EUVD
EUVD
•added 2026/10/28 9:16 p.m.•26 views

EUVD-2026-110041

ONNX: Out-of-bounds read in ConvTranspose shape inference via undersized weight rank...

6.2CVSS6.1AI score0.00178EPSS
SaveExploits0References5
Github Security Blog
Github Security Blog
•added 2026/10/28 9:15 p.m.•32 views

vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

For a model whose vocabulary size is an exact multiple of the embedding padding size 64 — e.g. any Llama-2-family model, vocab 32000 — a single request carrying a pre-tokenized prompt with token id equal to the vocab size 32000 passes vLLM's input-id validation but is one past the last embedding...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References6Affected Software1
osv_ghsa
osv_ghsa
•added 2026/10/28 9:15 p.m.•19 views

GHSA-Q97C-P368-75C4 vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

For a model whose vocabulary size is an exact multiple of the embedding padding size 64 — e.g. any Llama-2-family model, vocab 32000 — a single request carrying a pre-tokenized prompt with token id equal to the vocab size 32000 passes vLLM's input-id validation but is one past the last embedding...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References6
RedhatCVE
RedhatCVE
•added 2026/10/27 4:17 a.m.•13 views

CVE-2026-115922

A flaw was found in ONNX. This vulnerability allows an attacker to cause a Denial of Service DoS through excessive memory consumption by providing a specially crafted machine learning model. The issue occurs because tensor materialization routines resize memory arrays based on dimensions declared...

6.2CVSS6AI score0.00131EPSS
SaveExploits0References11
NVD
NVD
•added 2026/10/27 1:19 a.m.•25 views

CVE-2024-58399

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the...

6.9CVSS0.0012EPSS
SaveExploits0References6
osv_ubuntu
osv_ubuntu
•added 2026/10/27 1:19 a.m.•19 views

UBUNTU-CVE-2024-58399

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the...

6.9CVSS6.2AI score0.0012EPSS
SaveExploits0References10
Mend
Mend
•added 2026/10/27 12:33 a.m.•15 views

CVE-2024-58399

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the...

6.9CVSS6.2AI score0.0012EPSS
SaveExploits0References8
Cvelist
Cvelist
•added 2026/10/27 12:33 a.m.•38 views

CVE-2024-58399 llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the...

6.9CVSS0.0012EPSS
SaveExploits0References6
EUVD
EUVD
•added 2026/10/27 12:33 a.m.•16 views

EUVD-2024-55826

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the...

6.9CVSS6.2AI score0.0012EPSS
SaveExploits0References6
CVE
CVE
•added 2026/10/27 12:33 a.m.•31 views

CVE-2024-58399

The llama.cpp library (versions prior to b2731 ) contains an out-of-bounds read vulnerability within the llama_model_loader component. An attacker can exploit this by providing a crafted or truncated GGUF model file containing arbitrary 64-bit tensor offsets. This allows the attacker to read memo...

6.9CVSS6.2AI score0.0012EPSS
SaveExploits0References6
Vulnrichment
Vulnrichment
•added 2026/10/27 12:33 a.m.•9 views

CVE-2024-58399 llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the...

6.9CVSS6.2AI score0.0012EPSS
SaveExploits0References6
osv_cve
osv_cve
•added 2026/10/27 12:33 a.m.•20 views

CVE-2024-58399 llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the...

6.9CVSS6.2AI score
SaveExploits0References8
Positive Technologies
Positive Technologies
•added 2026/10/27 12:00 a.m.•21 views

PT-2026-125540

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llama model loader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash t...

6.9CVSS6.2AI score0.0012EPSS
SaveExploits0References7
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/10/27 12:00 a.m.•14 views

CVE-2024-58399: Out-of-bounds Read

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the...

6.9CVSS6.2AI score0.0012EPSS
SaveExploits0References2
UbuntuCve
UbuntuCve
•added 2026/10/27 12:00 a.m.•15 views

CVE-2024-58399

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the...

6.9CVSS6.2AI score0.0012EPSS
SaveExploits0References9
Snyk
Snyk
•added 2026/10/26 6:46 p.m.•26 views

Reachable Assertion

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Reachable Assertion via parseandvalidateimageinput in deepseekocr.py and deepseekocr2.py, where a zero-sum pixel tensor causes the function to retur...

7.1CVSS5.8AI score0.00397EPSS
SaveExploits0References2
Rows per page
Query Builder