Technology ❯ Artificial Intelligence

AI Security

Cybersecurity Vulnerabilities Data Privacy Prompt Injection Data Protection Threat Detection Risk Management Prompt Engineering Threat Management Threats

Google API Keys in Android Apps Now Unlock Gemini, Exposing Data and Costs

Researchers warn a design change grants old client keys access to Gemini, creating privacy and billing risk.

GrafanaGhost Vulnerability Lets AI Features Leak Data From Grafana

DeepMind Maps How the Open Web Can Hijack AI Agents

Ripple Adopts AI Security Program for XRP Ledger With Next Release Focused on Bug Fixes

Tech Giants Commit $12.5 Million to Linux Foundation Effort to Speed Open-Source Security Fixes

OpenAI to Acquire Promptfoo to Build Automated Security Into Frontier Agents

npm Worm 'SANDWORM_MODE' Exposed Targeting Developer and CI Secrets Through Typosquatted Packages

Microsoft Warns 'Summarize With AI' Links Are Poisoning Assistant Memories

OpenClaw’s Rapid Global Rollout Meets a Wave of Security Alarms

Microsoft Releases Scanner to Detect Backdoored Open-Weight LLMs

Microsoft Fixes 'Reprompt' Flaw That Enabled One-Click Data Theft From Copilot Personal

WWT Launches ARMOR, a Vendor-Agnostic Framework to Secure Enterprise AI

Widespread Flaws Let Prompt Injection Hijack AI Coding Tools and CI/CD Pipelines

Zscaler Shares Fall After Q1 Beat as Company Lifts Full-Year Outlook

Anthropic Rolls Out Claude Opus 4.5 With Chrome and Excel Integrations

Watchdog Urges OpenAI to Withdraw Sora 2 as Researchers Expose New Security Weakness

Veeam to Buy Securiti AI for $1.725 Billion to Create a Single Data Command Center

Anthropic-Led Study Finds 250 Poisoned Files Can Backdoor Large AI Models

Google Patches 'Gemini Trifecta' Flaws Enabling Indirect Prompt Injection

Salesforce Patches 'ForcedLeak' in Agentforce After Researchers Expose AI-Driven Data Leak Risk