596 matches found
End-of-Train and Head-of-Train Remote Linking Protocol (Update C)
RISK EVALUATION Successful exploitation of this vulnerability could allow an attacker to send their own brake control commands to the end-of-train device, causing a sudden stoppage of the train which may lead to a disruption of operations, or induce brake failure. 2. RECOMMENDED PRACTICES CISA...
Defending against Prompt Injection with a Few DefensiveTokens
When large language model LLM systems interact with external data to perform complex tasks, a new attack, namely prompt injection, becomes a significant threat. By injecting instructions into the data accessed by the system, the attacker is able to override the initial user task with an arbitrary...
Siemens TIA Administrator
SUMMARY Siemens TIA Administrator before V3.0.6 contains multiple vulnerabilities which could allow an attacker to escalate privilege or exceute arbitrary code during installations. Siemens has released a new version for TIA Administrator and recommends to update to the latest version. 2...
Siemens TIA Project-Server and TIA Portal
SUMMARY A vulnerability in TIA Project Server and TIA Portal could allow an attacker to cause a denial of service condition. Siemens has released new versions for several affected products and recommends to update to the latest versions. Siemens is preparing further fix versions and recommends...
Voltronic Power and PowerShield UPS monitoring software
RISK EVALUATION Successful exploitation of these vulnerabilities could allow an unauthenticated attacker remotely to make configuration changes, resulting in shutting down UPS connected devices or execution of arbitrary code. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures...
CISO Spotlight: Rick Bohm on Building Bridges, Taming AI, and the Future of API Security
Nestled in a log cabin high in the Rocky Mountains, Rick Bohm starts his day the same way he’s approached his career: intentionally, with a quiet commitment to learning and action. Boasting more than three decades of cybersecurity experience, Rick has watched tech evolve from dial-up ISPs to...
PTZOptics and Other Pan-Tilt-Zoom Cameras
RISK EVALUATION Successful exploitation of these vulnerabilities could allow an attacker to leak sensitive data, execute arbitrary commands, and access the admin web interface using hard-coded credentials. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the...
AVEVA PI Connector for CygNet
RISK EVALUATION Successful exploitation of these vulnerabilities could allow an attacker to persist arbitrary code in the administrative portal of the product or cause a denial-of-service condition. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of...
Siemens RUGGEDCOM APE1808
SUMMARY Palo Alto Networks has published 1 information on cross-site scripting vulnerability in PAN-OS. This advisory lists the related Siemens Industrial products affected by this vulnerability. Siemens is preparing fix versions and recommends countermeasures for products where fixes are not,...
MalGEN: a Generative Agent Framework for Modeling Malicious Software in Cybersecurity
The dual use nature of Large Language Models LLMs presents a growing challenge in cybersecurity. While LLM enhances automation and reasoning for defenders, they also introduce new risks, particularly their potential to be misused for generating evasive, AI crafted malware. Despite this emerging...
TokenBreak: Bypassing Text Classification Models through Token Manipulation
Natural Language Processing NLP models are used for text-related tasks such as classification and generation. To complete these tasks, input data is first tokenized from human-readable text into a format the model can understand, enabling it to make inferences and understand context. Text...
Privacy and Security Threat for OpenAI GPTs
Large language models LLMs demonstrate powerful information handling capabilities and are widely integrated into chatbot applications. OpenAI provides a platform for developers to construct custom GPTs, extending ChatGPT's functions and integrating external services. Since its release in November...
Preventing Adversarial AI Attacks against Autonomous Situational Awareness: a Maritime Case Study
Adversarial artificial intelligence AI attacks pose a significant threat to autonomous transportation, such as maritime vessels, that rely on AI components. Malicious actors can exploit these systems to deceive and manipulate AI-driven operations. This paper addresses three critical research...
A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?
Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of \emphComputer-Using Agents CUAs, capable of autonomously...
Exploit for CVE-2025-37899
This is the artefact repository associated with my blog post Ho...
Rockwell Automation FactoryTalk Historian ThingWorx
RISK EVALUATION Successful exploitation of this vulnerability could allow an attacker to launch XXE-based attacks on applications that accept malicious log4net configuration files. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of this...
Mitigating Cyber Risk in the Age of Open-Weight LLMs: Policy Gaps and Technical Realities
Open-weight general-purpose AI GPAI models offer significant benefits but also introduce substantial cybersecurity risks, as demonstrated by the offensive capabilities of models like DeepSeek-R1 in evaluations such as MITRE's OCCULT. These publicly available models empower a wider range of actors...
Vertiv Liebert RDU101 and UNITY
RISK EVALUATION Successful exploitation of these vulnerabilities could allow an attacker to cause a denial-of-service condition or achieve remote code execution 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of these vulnerabilities,...
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents
The growing adoption of large language models LLMs has led to a new paradigm in mobile computing--LLM-powered mobile AI agents--capable of decomposing and automating complex tasks directly on smartphones. However, the security implications of these agents remain largely unexplored. In this paper,...