HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense

Jailbreak attacks pose significant threats to large language models LLMs, enabling attackers to bypass safeguards. However, existing reactive defense approaches struggle to keep up with the rapidly evolving multi-turn jailbreaks, where attackers continuously deepen their attacks to exploit...

EUVD-2017-2261

Malware in sbrugna...

EUVD-2025-18431

Malicious code in bioql PyPI...

CVE-2025-6140 spdlog pattern_formatter-inl.h scoped_padder resource consumption

A vulnerability, which was classified as problematic, was found in spdlog up to 1.15.1. This affects the function scopedpadder in the library include/spdlog/patternformatter-inl.h. The manipulation leads to resource consumption. It is possible to launch the attack on the local host. The exploit h...

PT-2025-13834

Name of the Vulnerable Software and Affected Versions Open Asset Import Library Assimp version 5.4.3 Description A problematic vulnerability was found in the Open Asset Import Library Assimp. This issue affects the function Assimp::MDLImporter::ParseTextureColorData of the MDL File Handler...

CVE-2024-9437 Unauthenticated Denial of Service in transformeroptimus/superagi

SuperAGI version v0.0.14 is vulnerable to an unauthenticated Denial of Service DoS attack. The vulnerability exists in the resource upload request, where appending characters, such as dashes -, to the end of a multipart boundary in an HTTP request causes the server to continuously process each...