The growing adoption of AI coding assistants is introducing powerful productivity gains — but also new … Critical Command Injection in AI Coding Agent Exposed GitHub TokensRead more
ai security
Google Drive Introduces AI-Powered Ransomware Detection and File Restoration
Google has officially moved its ransomware detection and file restoration capabilities for Google Drive into General … Google Drive Introduces AI-Powered Ransomware Detection and File RestorationRead more
OpenClaw AI Agents Exposed to Indirect Prompt Injection, Enabling Silent Data Exfiltration
A newly uncovered class of vulnerabilities in OpenClaw autonomous AI agents demonstrates how attackers can weaponize … OpenClaw AI Agents Exposed to Indirect Prompt Injection, Enabling Silent Data ExfiltrationRead more
LangSmith Vulnerability: CVE‑2026‑25750 and How to Prevent Account Takeover
LangSmith, the AI observability platform behind many enterprise LLM stacks, ingests over one billion events per … LangSmith Vulnerability: CVE‑2026‑25750 and How to Prevent Account TakeoverRead more
State-Linked Threat Actors Used ChatGPT in Cyberattack Campaigns, OpenAI Confirms
OpenAI has publicly confirmed that state-linked cyber actors, including groups associated with China and Russia, exploited … State-Linked Threat Actors Used ChatGPT in Cyberattack Campaigns, OpenAI ConfirmsRead more
RoguePilot: GitHub Copilot Exploit Enables Full Repository Takeover
In a striking example of AI-driven security risks, researchers at Orca Security recently uncovered a critical … RoguePilot: GitHub Copilot Exploit Enables Full Repository TakeoverRead more
Anthropic Claude Targeted in Large-Scale AI Distillation Attacks
Artificial intelligence security has entered a new battleground. Anthropic has accused three major Chinese AI labs … Anthropic Claude Targeted in Large-Scale AI Distillation AttacksRead more
OpenClaw Exploitation: 30,000+ Instances Hacked
The OpenClaw exploitation wave marks a pivotal moment in AI security. Within 72 hours of its … OpenClaw Exploitation: 30,000+ Instances HackedRead more
LocalGPT: A Secure, Local-First AI Assistant Built in Rust
As AI assistants like ChatGPT and Claude dominate cloud-based workflows, user data increasingly risks exposure to … LocalGPT: A Secure, Local-First AI Assistant Built in RustRead more
LLMjacking Exposed: How Attackers Hijack and Monetize AI Endpoints
Large Language Models (LLMs) are rapidly becoming core enterprise infrastructure—but attackers are already exploiting the weakest … LLMjacking Exposed: How Attackers Hijack and Monetize AI EndpointsRead more