Towards Unifying Quantitative Security Benchmarking for Multi Agent Systems

Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks. One such risk is a cascading risk: a breach in one agent c...

CVE-2025-46686

Redis through 8.0.3 allows memory consumption via a multi-bulk command composed of many bulks, sent by an authenticated user. This occurs because the server allocates memory for the command arguments of every bulk, even when the command is skipped because of insufficient permissions. NOTE: this i...

CVE-2025-46686

Redis through 8.0.3 allows memory consumption via a multi-bulk command composed of many bulks, sent by an authenticated user. This occurs because the server allocates memory for the command arguments of every bulk, even when the command is skipped because of insufficient permissions. NOTE: this i...

hermes-agent

Hermes Agent ☤ The self-improving AI agent b...

Joint Advisory Issued on Protecting Against Interlock Ransomware

CISA, in partnership with the Federal Bureau of Investigation FBI, the Department of Health and Human Services, and the Multi-State Information Sharing and Analysis Center issued a joint Cybersecurity Advisory to help protect businesses and critical infrastructure organizations in North America a...

Exploit for CVE-2025-34085

Cyberlone Indonesia 🛠️ WordPress Simple File List RCE Scanner...

LENS-DF: Deepfake Detection and Temporal Localization for Long-Form Noisy Speech

This study introduces LENS-DF, a novel and comprehensive recipe for training and evaluating audio deepfake detection and temporal localization under complicated and realistic audio conditions. The generation part of the recipe outputs audios from the input dataset with several critical...

CVE-2025-7486 Ebook Store <= 5.8012 - Authenticated (Administrator+) Stored Cross-Site Scripting via Order Details

The Ebook Store plugin for WordPress is vulnerable to Stored Cross-Site Scripting via the Order Details in all versions up to, and including, 5.8012 due to insufficient input sanitization and output escaping. This makes it possible for authenticated attackers, with administrator-level access, to...

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems

Large Language Models LLMs deployed in enterprise settings e.g., as Microsoft 365 Copilot face novel security challenges. One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually extract confidential data. In this paper, we present a...

Scaling Decentralized Learning with FLock

Fine-tuning the large language models LLMs are prevented by the deficiency of centralized control and the massive computing and communication overhead on the decentralized schemes. While the typical standard federated learning FL supports data privacy, the central server requirement creates a...

CVE-2025-6719

The Terms descriptions plugin for WordPress is vulnerable to Stored Cross-Site Scripting via admin settings in all versions up to, and including, 3.4.8 due to insufficient input sanitization and output escaping. This makes it possible for authenticated attackers, with administrator-level...

CVE-2025-7431

The Knowledge Base plugin for WordPress is vulnerable to Stored Cross-Site Scripting via the plugin slug setting in all versions up to, and including, 2.3.1 due to insufficient input sanitization and output escaping. This makes it possible for authenticated attackers, with administrator-level...

CVE-2025-6719

The Terms descriptions plugin for WordPress is vulnerable to Stored Cross-Site Scripting via admin settings in all versions up to, and including, 3.4.8 due to insufficient input sanitization and output escaping. This makes it possible for authenticated attackers, with administrator-level...

CVE-2025-2799

The WP Event Manager – Events Calendar, Registrations, Sell Tickets with WooCommerce plugin for WordPress is vulnerable to Stored Cross-Site Scripting via the ‘tag-name’ parameter in all versions up to, and including, 3.1.49 due to insufficient input sanitization and output escaping. This makes i...

CVE-2025-6719 Terms descriptions <= 3.4.8 - Authenticated (Admin+) Stored Cross-Site Scripting

The Terms descriptions plugin for WordPress is vulnerable to Stored Cross-Site Scripting via admin settings in all versions up to, and including, 3.4.8 due to insufficient input sanitization and output escaping. This makes it possible for authenticated attackers, with administrator-level...

CVE-2025-6719

CVE-2025-6719 concerns the WordPress plugin Terms descriptions (

CVE-2025-7431

The Knowledge Base plugin for WordPress is vulnerable to Stored Cross-Site Scripting via the plugin slug setting in all versions up to, and including, 2.3.1 due to insufficient input sanitization and output escaping. This makes it possible for authenticated attackers, with administrator-level...

CVE-2025-7431

CVE-2025-7431 affects the WordPress Knowledge Base plugin. Vulnerability type: Stored Cross-Site Scripting via the plugin slug setting due to insufficient input sanitization and output escaping. Affected versions: all up to 2.3.1. Exploitation requires authenticated admin access (administrator+)....

CVE-2025-7431 Knowledge Base <= 2.3.1 - Authenticated (Administrator+) Stored Cross-Site Scripting via Plugin Slug

The Knowledge Base plugin for WordPress is vulnerable to Stored Cross-Site Scripting via the plugin slug setting in all versions up to, and including, 2.3.1 due to insufficient input sanitization and output escaping. This makes it possible for authenticated attackers, with administrator-level...

PT-2025-30002 · WordPress · Terms Descriptions

Name of the Vulnerable Software and Affected Versions: Terms descriptions plugin for WordPress versions prior to 3.4.9 Description: The Terms descriptions plugin for WordPress is susceptible to Stored Cross-Site Scripting through admin settings. Insufficient input sanitization and output escaping...