Lucene search
+L

13355 matches found

CVE
CVE
added 2026/02/02 8:14 p.m.43 views

CVE-2026-1778

SageMaker Python SDK (before v3.1.1 or v2.256.0) disables TLS certificate verification in the Triton Python backend during model import, allowing HTTPS requests to succeed with invalid/self-signed certificates. Affected versions: SDK <3.1.1 and

8.2CVSS5.4AI score0.00244EPSS
SaveExploits0References4
Vulnrichment
Vulnrichment
added 2026/02/02 8:14 p.m.7 views

CVE-2026-1778 TLS disabled by default in select aws/sagemaker-python-sdk configurations

Amazon SageMaker Python SDK before v3.1.1 or v2.256.0 disables TLS certificate verification for HTTPS connections made by the service when a Triton Python model is imported, incorrectly allowing for requests with invalid and self-signed certificates to succeed...

8.2CVSS5.4AI score0.00244EPSS
SaveExploits0References4
OSV
OSV
added 2026/02/02 5:43 p.m.11 views

GHSA-4R2X-XPJR-7CVV vLLM has RCE In Video Processing

Summary A chain of vulnerabilities in vLLM allow Remote Code Execution RCE: 1. Info Leak - PIL error messages expose memory addresses, bypassing ASLR 2. Heap Overflow - JPEG2000 decoder in OpenCV/FFmpeg has a heap overflow that lets us hijack code execution Result: Send a malicious video URL to...

9.8CVSS6.6AI score0.03723EPSS
SaveExploits0References20
Github Security Blog
Github Security Blog
added 2026/02/02 5:43 p.m.27 views

vLLM has RCE In Video Processing

Summary A chain of vulnerabilities in vLLM allow Remote Code Execution RCE: 1. Info Leak - PIL error messages expose memory addresses, bypassing ASLR 2. Heap Overflow - JPEG2000 decoder in OpenCV/FFmpeg has a heap overflow that lets us hijack code execution Result: Send a malicious video URL to...

9.8CVSS6.4AI score0.03723EPSS
SaveExploits0References20Affected Software1
NVD
NVD
added 2026/02/02 11:16 a.m.15 views

CVE-2026-0599

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET...

7.5CVSS0.22494EPSS
SaveExploits0References2
Cvelist
Cvelist
added 2026/02/02 10:36 a.m.280 views

CVE-2026-0599 Unbounded External Image Fetch in Validation Leads to Resource-Exhaustion DoS in huggingface/text-generation-inference

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET...

7.5CVSS0.22494EPSS
SaveExploits0References2
EUVD
EUVD
added 2026/02/02 10:36 a.m.10 views

EUVD-2026-5137

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET...

7.5CVSS5.5AI score0.22494EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
added 2026/02/02 10:36 a.m.7 views

CVE-2026-0599 Unbounded External Image Fetch in Validation Leads to Resource-Exhaustion DoS in huggingface/text-generation-inference

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET...

7.5CVSS5.5AI score0.22494EPSS
SaveExploits0References2
OSV
OSV
added 2026/02/02 10:36 a.m.13 views

CVE-2026-0599 Unbounded External Image Fetch in Validation Leads to Resource-Exhaustion DoS in huggingface/text-generation-inference

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET...

7.5CVSS7.1AI score
SaveExploits0References4
OSV
OSV
added 2026/02/02 9:02 a.m.5 views

MINI-26MX-479M-883P

Bulletin has no description...

7.5CVSS4.9AI score0.00838EPSS
SaveExploits0
CNNVD
CNNVD
added 2026/02/02 12:00 a.m.17 views

Text Generation Inference 资源管理错误漏洞

Text Generation Inference is a Rust, Python, and gRPC server developed by Hugging Face for text generation inference. Version 3.3.6 of Text Generation Inference contains a resource management vulnerability. This vulnerability stems from the unlimited acquisition of external images during input...

7.5CVSS7.1AI score0.22494EPSS
SaveExploits0References3
Positive Technologies
Positive Technologies
added 2026/02/02 12:00 a.m.12 views

PT-2026-5654

Name of the Vulnerable Software and Affected Versions huggingface/text-generation-inference version 3.3.6 huggingface/text-generation-inference versions prior to 3.3.7 Description A flaw exists in huggingface/text-generation-inference that allows unauthenticated remote attackers to cause a...

7.5CVSS7.4AI score0.22494EPSS
SaveExploits0References11
Packet Storm News
Packet Storm News
added 2026/02/02 12:00 a.m.10 views

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers

Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in causal language models. Our approach relies on two key findings: first, sleeper agents tend to memorize poisoning dat...

5.4AI score
SaveExploits0
Positive Technologies
Positive Technologies
added 2026/02/02 12:00 a.m.11 views

PT-2026-6363

Summary A chain of vulnerabilities in vLLM allow Remote Code Execution RCE: 1. Info Leak - PIL error messages expose memory addresses, bypassing ASLR 2. Heap Overflow - JPEG2000 decoder in OpenCV/FFmpeg has a heap overflow that lets us hijack code execution Result: Send a malicious video URL to...

9.8CVSS6.7AI score0.03723EPSS
SaveExploits0References7
OSV
OSV
added 2026/02/01 1:37 a.m.8 views

MINI-RH52-MVM8-RWC7

Bulletin has no description...

7CVSS7.2AI score0.00335EPSS
SaveExploits0
OSV
OSV
added 2026/02/01 1:37 a.m.6 views

MINI-QC85-J5CV-JM92

Bulletin has no description...

8.6CVSS5.8AI score0.00532EPSS
SaveExploits0
OSV
OSV
added 2026/02/01 1:33 a.m.7 views

MINI-H6CC-48RC-Q7WM

Bulletin has no description...

8.6CVSS7.2AI score0.00532EPSS
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/02/01 12:00 a.m.15 views

SMCP: Secure Model Context Protocol

Agentic AI systems built around large language models LLMs are moving away from closed, single-model frameworks and toward open ecosystems that connect a variety of agents, external tools, and resources. The Model Context Protocol MCP has emerged as a standard to unify tool access, allowing agent...

5.4AI score
SaveExploits0
OSV
OSV
added 2026/01/31 2:18 p.m.9 views

MINI-W94J-25XP-JV23

Bulletin has no description...

8.6CVSS5.8AI score0.00532EPSS
SaveExploits0
OSV
OSV
added 2026/01/31 2:18 p.m.6 views

MINI-V898-Q993-32CM

Bulletin has no description...

5.3CVSS5.8AI score0.00276EPSS
SaveExploits0
Rows per page
Query Builder