13523 matches found
STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns. This paper introduces Sequential Tool Attack Chaining STAC, a novel multi-turn attack framework that exploits agent tool use. STA...
MINI-4X32-M3FV-M3GR
Bulletin has no description...
MINI-68FP-P3W3-49MW
Bulletin has no description...
Unspecified Vulnerability in PyTorch (CNVD-2025-23278)
PyTorch is a Python package open-sourced by PyTorch. PyTorch suffers from a security vulnerability that stems from mishandling when compiling models containing torch.Tensor.tosparse and torch.Tensor.todense, which can be exploited by an attacker to cause a denial of service...
Quant Fever, Reasoning Blackholes, Schrodinger'S Compliance, and More: Probing GPT-OSS-20B
OpenAI's GPT-OSS family provides open-weight language models with explicit chain-of-thought CoT reasoning and a Harmony prompt format. We summarize an extensive security evaluation of GPT-OSS-20B that probes the model's behavior under different adversarial conditions. Using the Jailbreak Oracle J...
PyTorch Buffer Overflow Vulnerability (CNVD-2025-23287)
PyTorch is a Python package open-sourced by PyTorch. PyTorch= suffers from a buffer overflow vulnerability that stems from a boundary error in the PyTorch model compilation when handling untrusted input, which can be exploited by an attacker to cause a denial of service...
D-Link DIR-823X 命令注入漏洞
The D-Link DIR-823X is a wireless router from China's AUO D-Link. The D-Link DIR-823X suffers from a command injection vulnerability that can be exploited by an attacker to cause remote command execution...
MINI-WV89-XM83-233X
Bulletin has no description...
CVE-2025-7647 Insecure Temporary File Handling in run-llama/llama_index
The llama-index-core package, up to version 0.12.44, contains a vulnerability in the getcachedir function where a predictable, hardcoded directory path /tmp/llamaindex is used on Linux systems without proper security controls. This vulnerability allows attackers on multi-user systems to steal...
CVE-2025-7647
CVE-2025-7647 affects llama-index-core up to version 0.12.44, with a vulnerability in get_cache_dir() that uses a predictable, hardcoded directory path (/tmp/llama_index) on Linux. On multi-user Linux systems, this insecure temporary directory can enable local attackers to steal proprietary model...
CVE-2025-60142
Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in DaganLev Simple Meta Tags simple-meta-tags allows DOM-Based XSS.This issue affects Simple Meta Tags: from n/a through = 1.5...
LlamaIndex 安全漏洞
LlamaIndex is a data framework for LLM applications from the LlamaIndex open source. A security vulnerability exists in LlamaIndex version 0.12.44 and earlier, which stems from the use of hard-coded paths and lack of security controls in the getcachedir function, which could lead to model stealin...
AutoML in Cybersecurity: An Empirical Study
Automated machine learning AutoML has emerged as a promising paradigm for automating machine learning ML pipeline design, broadening AI adoption. Yet its reliability in complex domains such as cybersecurity remains underexplored. This paper systematically evaluates eight open-source AutoML...
CVE-2025-10973
A flaw has been found in JackieDYH Resume-management-system up to fb6b857d852dd796e748ce30c606fe5e61c18273. Affected by this issue is some unknown functionality of the file /admin/show.php. This manipulation of the argument userid causes sql injection. The attack may be initiated remotely. The...
CVE-2025-11046 Tencent WeKnora test testEmbeddingModel server-side request forgery
A security flaw has been discovered in Tencent WeKnora 0.1.0. This impacts the function testEmbeddingModel of the file /api/v1/initialization/embedding/test. The manipulation of the argument baseUrl results in server-side request forgery. The attack can be launched remotely. The exploit has been...
CVE-2025-11046 Tencent WeKnora test testEmbeddingModel server-side request forgery
A security flaw has been discovered in Tencent WeKnora 0.1.0. This impacts the function testEmbeddingModel of the file /api/v1/initialization/embedding/test. The manipulation of the argument baseUrl results in server-side request forgery. The attack can be launched remotely. The exploit has been...
CVE-2025-11046 Tencent WeKnora test testEmbeddingModel server-side request forgery
A security flaw has been discovered in Tencent WeKnora 0.1.0. This impacts the function testEmbeddingModel of the file /api/v1/initialization/embedding/test. The manipulation of the argument baseUrl results in server-side request forgery. The attack can be launched remotely. The exploit has been...
MAL-2025-47689 Malicious code in model-viewer-docs (npm)
--- -= Per source details. Do not edit below this line.=-...
Malicious code in model-viewer-docs (npm)
--- -= Per source details. Do not edit below this line.=-...
CVE-2025-60142
CVE-2025-60142 – WordPress: Simple Meta Tags plugin (versions up to 1.5) exposes a DOM-based XSS due to improper neutralization of input during web page generation. The vulnerability is classified as an authenticated issue (Contributor+ required) with stored XSS. The linked docs indicate the vuln...