13316 matches found
Mapping the Exploitation Surface: A 10,000-Trial Taxonomy of What Makes LLM Agents Exploit Vulnerabilities
LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on approximately 10,000 trials across seven models, 37 prompt...
PT-2026-30687
text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.1.1, users can save extention settings in "py" format and in the app root directory. This allows to overwrite python files, for instance the "download-model.py" file could be overwritten. Then, thi...
chyrp-lite 安全漏洞
Chyrp-Lite is a self-hosted blog and website platform developed by Daniel Pimley. Versions of Chyrp-Lite prior to version 2026.01 contained security vulnerabilities. These vulnerabilities stemmed from insecure direct object references or bulk assignment issues in the Post model, which could lead ...
PT-2026-30585
The setup: 4 agents chain off each other in a loop, each reacting to the previous response. Dominus — finds a new vulnerability angle from the CISA KEV catalog Axiom — adds one new technical detail to the finding Cipher — identifies one specific flaw in the previous argument Vector — names one...
Broken by Default: A Formal Verification Study of Security Vulnerabilities in AI-Generated Code
AI coding assistants are now used to generate production code in security-sensitive domains, yet the exploitability of their outputs remains unquantified. We address this gap with Broken by Default: a formal verification study of 3,500 code artifacts generated by seven frontier LLMs across 500...
vLLM 安全漏洞
vLLM is an open-source LLM-based inference and service engine that features high throughput and efficient memory usage. Versions of vLLM prior to 0.1.0 to 0.19.0 contained security vulnerabilities. These vulnerabilities stemmed from the lack of upper limit validation for the n parameter in the...
MINI-W59P-554P-455V
Bulletin has no description...
MINI-RQ9H-X256-RPWR
Bulletin has no description...
MINI-CH34-X32H-XVWH
Bulletin has no description...
MINI-88HR-VCM5-M34V
Bulletin has no description...
MINI-822C-W965-RHH7
Bulletin has no description...
MINI-M623-9GCR-M429
Bulletin has no description...
MINI-M3PM-F95X-WGGH
Bulletin has no description...
whitehathackerai
🛡️ WhiteHatHacker AI Autonomous Bug Bounty Hunter — Power...
CVE-2026-5546
A flaw has been found in Campcodes Complete Online Learning Management System 1.0. This impacts the function addlesson of the file /application/models/Crudmodel.php. This manipulation causes unrestricted upload. It is possible to initiate the attack remotely. The exploit has been published and ma...
CVE-2026-5546 Campcodes Complete Online Learning Management System Crud_model.php add_lesson unrestricted upload
A flaw has been found in Campcodes Complete Online Learning Management System 1.0. This impacts the function addlesson of the file /application/models/Crudmodel.php. This manipulation causes unrestricted upload. It is possible to initiate the attack remotely. The exploit has been published and ma...
CVE-2026-5546
CVE-2026-5546 affects Campcodes Complete Online Learning Management System 1.0; the flaw is in Crud_model.php add_lesson, where a manipulation leads to unrestricted file uploads. The issue can be triggered remotely, and the exploit has been published. No remediation details are provided in the av...
CVE-2026-5546
A flaw has been found in Campcodes Complete Online Learning Management System 1.0. This impacts the function addlesson of the file /application/models/Crudmodel.php. This manipulation causes unrestricted upload. It is possible to initiate the attack remotely. The exploit has been published and ma...
CVE-2026-5546 Campcodes Complete Online Learning Management System Crud_model.php add_lesson unrestricted upload
A flaw has been found in Campcodes Complete Online Learning Management System 1.0. This impacts the function addlesson of the file /application/models/Crudmodel.php. This manipulation causes unrestricted upload. It is possible to initiate the attack remotely. The exploit has been published and ma...
EUVD-2026-19009
A flaw has been found in Ollama up to 18.1. This issue affects some unknown processing of the file server/download.go of the component Model Pull API. Executing a manipulation can lead to server-side request forgery. The attack can be launched remotely. The vendor was contacted early about this...