Governing the Unseen Risks of GenAI: Why Bias Mitigation and Human Oversight Matter Most
Enterprise adoption of generative AI (GenAI) is accelerating at a pace far beyond previous technological advances, with organizations using...
Prompt Injection
The Trojan Prompt: How GenAI is Turning Staff into Unwitting Insider Threats
When a wooden horse was wheeled through the gates of Troy, it was welcomed as a gift but hid...
Why API Security Will Drive AppSec in 2026 and Beyond
The way software is built is being rewritten in real-time. Large language model (LLM) integration, agents and model context protocol (MCP) connection turn a simple app...
The New Frontier of Cyber Threats: Unpacking Prompt Injection, Model Poisoning and Adversarial Attacks in AI Security
As artificial intelligence (AI) continues its relentless integration into both individual and enterprise ecosystems, it simultaneously emerges as a...
Crafted URLs can trick OpenAI Atlas into running dangerous commands
Crafted URLs can trick OpenAI Atlas into running dangerous commands Pierluigi Paganini October 27, 2025 Attackers can trick OpenAI Atlas...
Humanoid Robots are Walking Trojan Horses — And They’re Already in the Workplace
A new study reveals severe security flaws in the Unitree G1 humanoid robot, exposing risks from Bluetooth backdoors to hidden...
ForcedLeak flaw in Salesforce Agentforce exposes CRM data via Prompt Injection
ForcedLeak flaw in Salesforce Agentforce exposes CRM data via Prompt Injection Pierluigi Paganini September 27, 2025 Researchers disclosed a critical...
