OpenAI’s Guardrails Can Be Bypassed by Simple Prompt Injection Attack

Just weeks after its release, OpenAI’s Guardrails system was quickly bypassed by researchers. Read how simple prompt injection attacks fooled the system’s AI judges and exposed an ongoing security concern for OpenAI...

Why Unmonitored JavaScript Is Your Biggest Holiday Security Risk

Think your WAF has you covered? Think again. This holiday season, unmonitored JavaScript is a critical oversight allowing attackers to steal payment data while your WAF and intrusion detection systems see nothing. With the 2025 shopping season weeks away, visibility gaps must close now. Get the...

Why Unmonitored JavaScript Is Your Biggest Holiday Security Risk

Think your WAF has you covered? Think again. This holiday season, unmonitored JavaScript is a critical oversight allowing attackers to steal payment data while your WAF and intrusion detection systems see nothing. With the 2025 shopping season weeks away, visibility gaps must close now. Get the...

EUVD-2025-33967

Ericsson Network Manager versions prior to ENM 25.2 GA contain a vulnerability that, if exploited, can exfiltrate limited data or redirect victims to other sites or domains...

CVE-2025-31995 HCL Unica MaxAI Workbench is vulnerable to improper input validation

HCL Unica MaxAI Workbench is vulnerable to improper input validation. This allows attackers to exploit vulnerabilities such as SQL Injection, XSS, or command injection, leading to unauthorized access or data breaches, etc...

Attacks by Content: Automated Fact-Checking Is an AI Security Issue

When AI agents retrieve and reason over external documents, adversaries can manipulate the data they receive to subvert their behaviour. Previous research has studied indirect prompt injection, where the attacker injects malicious instructions. We argue that injection of instructions is not...

HCL Unica MaxAI Workbench 安全漏洞

HCL Unica MaxAI Workbench is an artificial intelligence modeling and prediction module from HCL India. A security vulnerability exists in HCL Unica MaxAI Workbench, which stems from improper input validation and could lead to SQL injection, cross-site scripting, or command injection attacks, whic...

PT-2025-41762

Name of the Vulnerable Software and Affected Versions Ericsson Network Manager versions prior to 25.2 GA Description The software contains a flaw that could allow for the exfiltration of limited data or the redirection of users to other websites or domains. Recommendations Update to version 25.2 ...

Navigating the Dual-Use Nature and Security Implications of Reconfigurable Intelligent Surfaces in Next-Generation Wireless Systems

Reconfigurable intelligent surface RIS technology offers significant promise in enhancing wireless communication systems, but its dual-use potential also introduces substantial security risks. This survey explores the security implications of RIS in next-generation wireless networks. We first...

PT-2025-46966

Уязвимость почтового клиента Blue Mail связана с нарушением механизма защиты данных. Эксплуатация уязвимости может позволить нарушителю, действующему удалённо, проводить фишинговые атаки...

Tomofun Furbo 360和Tomofun Furbo Mini 信任管理问题漏洞

Tomofun Furbo 360 and Tomofun Furbo Mini are both smart pet cameras from Tomofun Corporation of Taiwan, China. A trust management issue vulnerability exists in Tomofun Furbo 360 FB0035FW036 and earlier versions and Tomofun Furbo Mini MC0020FW074 and earlier versions, which stems from improper...

Tomofun Furbo 360和Tomofun Furbo Mini 信任管理问题漏洞

Tomofun Furbo 360 and Tomofun Furbo Mini are both smart pet cameras from Tomofun Corporation of Taiwan, China. A trust management issue vulnerability exists in Tomofun Furbo 360 FB0035FW036 and earlier versions and Tomofun Furbo Mini MC0020FW074 and earlier versions, which stems from the presence...

Tomofun Furbo 360 安全漏洞

Tomofun Furbo 360 is a smart pet camera from Tomofun Corporation of Taiwan, China. A security vulnerability exists in Tomofun Furbo 360 FB0035FW036 and prior versions, which stems from a resource consumption issue in the file upload component that could lead to remote attacks...

Hackers Turn Velociraptor DFIR Tool Into Weapon in LockBit Ransomware Attacks

Threat actors are abusing Velociraptor, an open-source digital forensics and incident response DFIR tool, in connection with ransomware attacks likely orchestrated by Storm-2603 aka CL-CRI-1040 or Gold Salem, which is known for deploying the Warlock and LockBit ransomware. The threat actor's use ...

CVE-2025-52624

A vulnerability Bypass of the script allowlist configuration in HCL AION. An incorrectly configured Content-Security-Policy header may allow unauthorized scripts to execute, increasing the risk of cross-site scripting and other injection-based attacks.This issue affects AION: 2.0...

EulerOS 2.0 SP11 : pam (EulerOS-SA-2025-2207)

According to the versions of the pam package installed, the EulerOS installation on the remote host is affected by the following vulnerabilities : A flaw was found in linux-pam. The pamnamespace module may improperly handle user-controlled paths, allowing local users to exploit symlink attacks an...

EulerOS 2.0 SP11 : pam (EulerOS-SA-2025-2239)

According to the versions of the pam package installed, the EulerOS installation on the remote host is affected by the following vulnerabilities : A flaw was found in linux-pam. The pamnamespace module may improperly handle user-controlled paths, allowing local users to exploit symlink attacks an...

CVE-2025-52624: Improper Neutralization of Input During Web Page Generation

A vulnerability Bypass of the script allowlist configuration in HCL AION. An incorrectly configured Content-Security-Policy header may allow unauthorized scripts to execute, increasing the risk of cross-site scripting and other injection-based attacks.This issue affects AION: 2.0...

HCL AION 安全漏洞

HCL AION is an AI lifecycle management platform from HCL India. HCL AION suffers from a security vulnerability that stems from a script whitelist configuration bypass and a misconfigured Content-Security-Policy header, which can be exploited by an attacker to cause cross-site scripting and other...

Websoft HCM Automation Software XSS

The vulnerability of Websoft HCM’s automation software for HR processes is related to the lack of measures taken to protect the website structure. Exploiting this vulnerability allows attackers to perform cross-site scripting attacks remotely...