EUVD-2022-0862

Malicious code in bioql PyPI...

EUVD-2022-4271

Malicious code in bioql PyPI...

EUVD-2022-38894

Malicious code in bioql PyPI...

Directory Traversal

Overview strands-agents is an A model-driven approach to building AI agents in just a few lines of code Affected versions of this package are vulnerable to Directory Traversal via the FileSessionManager.getsessionpath, FileSessionManager.getagentpath, S3SessionManager.getsessionpath, and...

RedCodeAgent: Automatic Red-Teaming Agent against Diverse Code Agents

Code agents have gained widespread adoption due to their strong code generation capabilities and integration with code interpreters, enabling dynamic execution, debugging, and interactive programming capabilities. While these advancements have streamlined complex workflows, they have also...

A Cybersecurity AI Agent Selection and Decision Support Framework

This paper presents a novel, structured decision support framework that systematically aligns diverse artificial intelligence AI agent architectures, reactive, cognitive, hybrid, and learning, with the comprehensive National Institute of Standards and Technology NIST Cybersecurity Framework CSF...

Breaking the Code: Security Assessment of AI Code Agents through Systematic Jailbreaking Attacks

Code-capable large language model LLM agents are increasingly embedded into software engineering workflows where they can read, write, and execute code, raising the stakes of safety-bypass "jailbreak" attacks beyond text-only settings. Prior evaluations emphasize refusal or harmful-text detection...

WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents

Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection attacks, but none have been systematically evaluated for web agents. In this work, we bridge this gap by presenting the first...

Abusing Notion’s AI Agent for Data Theft

Notion just released version 3.0, complete with AI agents. Because the system contains Simon Willson's lethal trifecta, it's vulnerable to data theft though prompt injection. First, the trifecta: The lethal trifecta of capabilities is: Access to your private data --one of the most common purposes...

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...

Takedown: How It's Done in Modern Coding Agent Exploits

Coding agents, which are LLM-driven agents specialized in software development, have become increasingly prevalent in modern programming environments. Unlike traditional AI coding assistants, which offer simple code completion and suggestions, modern coding agents tackle more complex tasks with...

SafeSearch: Automated Red-Teaming for the Safety of LLM-Based Search Agents

Search agents connect LLMs to the Internet, enabling access to broader and more up-to-date information. However, unreliable search results may also pose safety threats to end users, establishing a new threat surface. In this work, we conduct two in-the-wild experiments to demonstrate both the...

CVE-2025-10542

iMonitor EAM 9.6394 ships with default administrative credentials that are also displayed within the management client’s connection dialog. If the administrator does not change these defaults, a remote attacker can authenticate to the EAM server and gain full control over monitored agents and dat...

SecureAgentBench: Benchmarking Secure Code Generation under Realistic Vulnerability Scenarios

Large language model LLM powered code agents are rapidly transforming software engineering by automating tasks such as testing, debugging, and repairing, yet the security risks of their generated code have become a critical concern. Existing benchmarks have offered valuable insights but remain...

Introducing Microsoft Marketplace — Thousands of solutions. Millions of customers. One Marketplace.

A new breed of industry-leading company is taking shape — Frontier Firms. These organizations blend human ambition with AI-powered technology to reshape how innovation is scaled, work is orchestrated and value is created. They’re accelerating AI transformation to enrich employee experiences,...

CVE-2025-10542

iMonitor EAM 9.6394 ships with default administrative credentials that are also displayed within the management client’s connection dialog. If the administrator does not change these defaults, a remote attacker can authenticate to the EAM server and gain full control over monitored agents and dat...

ForcedLeak Flaw in Salesforce Agentforce AI Agent Exposed CRM Data

Cybersecurity firm Noma Security reveals ForcedLeak, a critical flaw in Salesforce Agentforce that allowed data theft. Learn what companies need to do now to secure AI agents...

PT-2025-39391

Name of the Vulnerable Software and Affected Versions iMonitor EAM version 9.6394 Description The software ships with default administrative credentials that are displayed within the management client’s connection dialog. If the administrator does not change these defaults, a remote attacker can...

EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email Defense

Modern email spam and phishing attacks have evolved far beyond keyword blacklists or simple heuristics. Adversaries now craft multi-modal campaigns that combine natural-language text with obfuscated URLs, forged headers, and malicious attachments, adapting their strategies within days to bypass...

PhishLumos: an Adaptive Multi-Agent System for Proactive Phishing Campaign Mitigation

Phishing attacks are a significant societal threat, disproportionately harming vulnerable populations and eroding trust in essential digital services. Current defenses are often reactive, failing against modern evasive tactics like cloaking that conceal malicious content. To address this, we...