A new ranking of Model Context Protocol weaknesses highlights critical risks—from prompt injection to command injection—and provides a roadmap for securing the foundations of agentic AI.
The post Top 25 MCP Vulnerabilities Reveal How AI Agents Can Be Exploited appeared first on SecurityWeek.
The Canada-based company has emerged from stealth with autonomous AI agents designed to manage and operate the security and IT stack.
The post Mycroft Raises $3.5 Million for AI-Powered Security and Compliance Platform appeared first on SecurityWeek.
The AI agent was able to solve different types of CAPTCHAs and adjusted its cursor movements to better mimic human behavior.
The post ChatGPT Tricked Into Solving CAPTCHAs appeared first on SecurityWeek.
OpenAI has fixed this zero-click attack method called by researchers ShadowLeak.
The post ChatGPT Deep Research Targeted in Server-Side Data Theft Attack appeared first on SecurityWeek.
Irregular is testing the cybersecurity capabilities of AI models, including Anthropic’s Claude and OpenAI’s ChatGPT.
The post Irregular Raises $80 Million for AI Security Testing Lab appeared first on SecurityWeek.
The startup provides an authentication stack that secures both incoming authentication and outgoing agent actions.
The post Scalekit Raises $5.5 Million to Secure AI Agent Authentication appeared first on SecurityWeek.
Acquisition extends CrowdStrike’s Falcon platform into AI security, introducing AI Detection and Response (AIDR) to protect enterprise models, agents, and applications across the full AI lifecycle.
The post CrowdStrike to Acquire Pangea to Launch AI Detection and Response (AIDR) appeared first on SecurityWeek.
Move highlights rising demand for AI-native security as enterprises face new risks from generative models and autonomous agents
The post Check Point to Acquire AI Security Firm Lakera appeared first on SecurityWeek.
Researchers show how a crafted calendar invite can trigger ChatGPT to exfiltrate sensitive emails.
The post ChatGPT’s Calendar Integration Can Be Exploited to Steal Emails appeared first on SecurityWeek.
Join the webinar as we reveal a new model for AI pen testing – one grounded in social engineering, behavioral manipulation, and even therapeutic dialogue.
The post Webinar Today: Breaking AI – Inside the Art of LLM Pen Testing appeared first on SecurityWeek.
Impostazioni privacy
Questo sito utilizza i cookie per migliorare la tua esperienza di navigazione su questo sito.
