Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks

Vibe coding is a new programming paradigm in which human engineers instruct large language model LLM agents to complete complex coding tasks with little supervision. Although it is increasingly adopted, are vibe coding outputs really safe to deploy in production? To answer this question, we propo...

COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers

This paper studies how multimodal large language models MLLMs undermine the security guarantees of visual CAPTCHA. We identify the attack surface where an adversary can cheaply automate CAPTCHA solving using off-the-shelf models. We evaluate 7 leading commercial and open-source MLLMs across 18...

Systems Security Foundations for Agentic Computing

This paper articulates short- and long-term research problems in AI agent security and privacy, using the lens of computer systems security. This approach examines end-to-end security properties of entire systems, rather than AI models in isolation. While we recognize that hardening a single mode...

Securing Large Language Models (LLMs) from Prompt Injection Attacks

Large Language Models LLMs are increasingly being deployed in real-world applications, but their flexibility exposes them to prompt injection attacks. These attacks leverage the model's instruction-following ability to make it perform malicious tasks. Recent work has proposed JATMO, a task-specif...

LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems

Large Language Model LLM-based agents have demonstrated remarkable capabilities in reasoning, planning, and tool usage. The recently proposed Model Context Protocol MCP has emerged as a unifying framework for integrating external tools into agent systems, enabling a thriving open ecosystem of...

Large Language Models Cannot Reliably Detect Vulnerabilities in JavaScript: The First Systematic Benchmark and Evaluation

Researchers have proposed numerous methods to detect vulnerabilities in JavaScript, especially those assisted by Large Language Models LLMs. However, the actual capability of LLMs in JavaScript vulnerability detection remains questionable, necessitating systematic evaluation and comprehensive...

Reverse Engineering and Control-Aware Security Analysis of the ArduPilot UAV Framework

Unmanned Aerial Vehicle UAV technologies are gaining high interest for many domains, which makes UAV security of utmost importance. ArduPilot is among the most widely used open-source autopilot UAV frameworks; yet, many studies demonstrate the vulnerabilities affecting such systems. Vulnerabiliti...

Red Teaming Large Reasoning Models

Large Reasoning Models LRMs have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains of thought CoT. However, these models introduce novel safety and reliability risks, such as CoT-hijacking and...

Prompt Injection Through Poetry

In a new paper, "Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models," researchers found that turning LLM prompts into poetry resulted in jailbreaking the models: Abstract : We present evidence that adversarial poetry functions as a universal single-turn...

Evaluating LLMs for One-Shot Patching of Real and Artificial Vulnerabilities

Automated vulnerability patching is crucial for software security, and recent advancements in Large Language Models LLMs present promising capabilities for automating this task. However, existing research has primarily assessed LLMs using publicly disclosed vulnerabilities, leaving their...

CVE-2025-66252

Infinite Loop Denial of Service via Failed File Deletion in DB Electronica Telecomunicazioni S.p.A. Mozart FM Transmitter versions 30, 50, 100, 300, 500, 1000, 2000, 3000, 3500, 6000, 7000 allows an attacker to perform Infinite loop when unlink fails in statuscontents.php causing DoS. Due to the...

CVE-2025-66251

Unauthenticated Path Traversal with Arbitrary File Deletion in DB Electronica Telecomunicazioni S.p.A. Mozart FM Transmitter versions 30, 50, 100, 300, 500, 1000, 2000, 3000, 3500, 6000, 7000 allows an attacker to perform The deletehidden parameter allows path traversal deletion of arbitrary .tgz...

EUVD-2025-199673

PostgreSQL SQL Injection statussql.php in DB Electronica Telecomunicazioni S.p.A. Mozart FM Transmitter versions 30, 50, 100, 300, 500, 1000, 2000, 3000, 3500, 6000, 7000 allows an attacker to perform SQL injection via sw1 and sw2 parameters in statussql.php. The statussql.php endpoint constructs...

CVE-2025-66256

The CVE concerns a vulnerability in DB Electronica Telecomunicazioni S.p.A. Mozart FM Transmitter series (versions 30–7000) where the /var/tdf/patch_contents.php endpoint allows unauthenticated, unrestricted file uploads. There is no file type validation, MIME checking, or size restriction beyond...

CVE-2025-66251 Unauthenticated Path Traversal with Arbitrary File Deletion

Unauthenticated Path Traversal with Arbitrary File Deletion in DB Electronica Telecomunicazioni S.p.A. Mozart FM Transmitter versions 30, 50, 100, 300, 500, 1000, 2000, 3000, 3500, 6000, 7000 allows an attacker to perform The deletehidden parameter allows path traversal deletion of arbitrary .tgz...

CVE-2025-66250

CVE-2025-66250 affects DB Electronica Telecomunicazioni S.p.A. Mozart FM Transmitter firmware (models 30, 50, 100, 300, 500, 1000, 2000, 3000, 3500, 6000, 7000). The vulnerability is an unauthenticated arbitrary file upload via the /var/tdf/status_contents.php endpoint in the status_contents.php ...

PT-2025-48103

Name of the Vulnerable Software and Affected Versions DB Electronica Telecomunicazioni S.p.A. Mozart FM Transmitter versions 30, 50, 100, 300, 500, 1000, 2000, 3000, 3500, 6000, 7000 Description An unauthenticated path traversal issue exists that allows for arbitrary file deletion. The deletehidd...

Constructing and Benchmarking: A Labeled Email Dataset for Text-Based Phishing and Spam Detection Framework

Phishing and spam emails remain a major cybersecurity threat, with attackers increasingly leveraging Large Language Models LLMs to craft highly deceptive content. This study presents a comprehensive email dataset containing phishing, spam, and legitimate messages, explicitly distinguishing betwee...

PT-2025-48109

Name of the Vulnerable Software and Affected Versions Mozart FM Transmitter versions 30 through 7000 Description The software contains a flaw that allows for unauthenticated deletion of arbitrary files. Specifically, the deletepatch parameter within the patch contents.php file permits the deletio...

A Safety and Security Framework for Real-World Agentic Systems

This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attributes of individual models but also emergent properties arising from the dynamic interactions among models, orchestrator...