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...

The vulnerability of the Wazuh API’s Agent Configuration component in the wazuh-dashboard platform, which is used for security monitoring and threat detection. This vulnerability allows attackers to obtain credentials for registering new agents.

The vulnerability of the Wazuh API’s Agent Configuration component in the wazuh-dashboard platform, which is used for security monitoring and threat detection, is related to deficiencies in access control. Exploiting this vulnerability could allow a malicious actor to obtain credentials for...

CVE-2025-53360

pluginsGLPI's Database Inventory Plugin "manages" the Teclib' inventory agents in order to perform an inventory of the databases present on the workstation. In versions prior to 1.0.3, any authenticated user could send requests to agents. This issue has been patched in version 1.0.3...

CVE-2025-55074

Mattermost versions 10.11.x = 10.11.3, 10.5.x = 10.5.11 fail to enforce access permissions on the Agents plugin which allows other users to determine when users had read channels via channel member objects...

Huawei and Chinese Surveillance

This quote is from House of Huawei: The Secret History of China 's Most Powerful Company. "Long before anyone had heard of Ren Zhengfei or Huawei, Wan Runnan had been China's star entrepreneur in the 1980s, with his company, the Stone Group, touted as "China's IBM." Wan had believed that economic...

Charting the future of SOC: Human and AI collaboration for better security

Security operations centers are under pressure from unprecedented scale and complexity. Speed, precision, and consistency matter more than ever, and AI is everywhere—but hype alone doesn’t solve the challenge. This blog shares our journey and insights from building autonomous AI agents for MDR...

Charting the future of SOC: Human and AI collaboration for better security

Security operations centers are under pressure from unprecedented scale and complexity. Speed, precision, and consistency matter more than ever, and AI is everywhere—but hype alone doesn’t solve the challenge. This blog shares our journey and insights from building autonomous AI agents for MDR...

Securing the Model Context Protocol (MCP): Risks, Controls, and Governance

The Model Context Protocol MCP replaces static, developer-controlled API integrations with more dynamic, user-driven agent systems, which also introduces new security risks. As MCP adoption grows across community servers and major platforms, organizations encounter threats that existing AI...

Amazon Is Using Specialized AI Agents for Deep Bug Hunting

Born out of an internal hackathon, Amazon’s Autonomous Threat Analysis system uses a variety of specialized AI agents to detect weaknesses and propose fixes to the company’s platforms...

Lack of Sufficient Guardrails Lead to Excessive Agency (LLM08) in Some LLM Applications

Overview Retell AI's API creates AI voice agents that have excessive permissions and functionality, as a result of insufficient amounts of guardrails. As a result, attackers can exploit this and conduct large scale social engineering, phishing, and misinformation campaigns. Description Retell AI...

LLMs As Firmware Experts: A Runtime-Grown Tree-Of-Agents Framework

Large Language Models LLMs and their agent systems have recently demonstrated strong potential in automating code reasoning and vulnerability detection. However, when applied to large-scale firmware, their performance degrades due to the binary nature of firmware, complex dependency structures, a...

AI as Cyberattacker

From Anthropic: In mid-September 2025, we detected suspicious activity that later investigation determined to be a highly sophisticated espionage campaign. The attackers used AI’s “agentic” capabilities to an unprecedented degree­--using AI not just as an advisor, but to execute the cyberattacks...

PT-2025-47728

Name of the Vulnerable Software and Affected Versions ELEX WordPress HelpDesk & Customer Ticketing System plugin versions through 3.3.1 Description The ELEX WordPress HelpDesk & Customer Ticketing System plugin for WordPress has a flaw that allows unauthorized data modification. A missing...

Securing AI Agents against Prompt Injection Attacks

Retrieval-augmented generation RAG systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive benchmark for evaluating prompt injection risks in RAG-enabled A...

Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming

Generative AI is reshaping offensive cybersecurity by enabling autonomous red team agents that can plan, execute, and adapt during penetration tests. However, existing approaches face trade-offs between generality and specialization, and practical deployments reveal challenges such as...

Incorrect Default Permissions

Overview Affected versions of this package are vulnerable to Incorrect Default Permissions via the Agents plugin process. An attacker can access information about when users have read channels by querying channel member objects. Remediation Upgrade...

Mattermost allows other users to determine when users had read channels via channel member objects

Mattermost versions 10.11.x = 10.11.3, and 10.5.x = 10.5.11 fail to enforce access permissions on the Agents plugin which allows other users to determine when users had read channels via channel member objects...

EUVD-2025-198045

Mattermost allows other users to determine when users had read channels via channel member objects...

GHSA-9HH7-6558-QFP2 Mattermost allows other users to determine when users had read channels via channel member objects

Mattermost versions 10.11.x = 10.11.3, and 10.5.x = 10.5.11 fail to enforce access permissions on the Agents plugin which allows other users to determine when users had read channels via channel member objects...

CVE-2025-53360

pluginsGLPI's Database Inventory Plugin "manages" the Teclib' inventory agents in order to perform an inventory of the databases present on the workstation. In versions prior to 1.0.3, any authenticated user could send requests to agents. This issue has been patched in version 1.0.3...