A newly disclosed AWS Kiro vulnerability shows how a hidden line of text on a webpage … Hidden Web Text Can Trigger AWS Kiro RCERead more
prompt injection
Jailbroken AI Models Are Becoming Offensive Security Tools
A Russian-speaking threat actor known as Trim has reportedly turned jailbroken AI models into an automated … Jailbroken AI Models Are Becoming Offensive Security ToolsRead more
Microsoft Warns Claude Code GitHub Action Flaw Exposes CI/CD Pipeline Secrets
AI-powered coding assistants are rapidly integrating into software development pipelines, but their automated execution layers introduce … Microsoft Warns Claude Code GitHub Action Flaw Exposes CI/CD Pipeline SecretsRead more
Zero-Click AI Attack Chains Bypass Human Oversight in Agentic Systems
The rapid rise of autonomous AI has introduced a new class of cybersecurity risks, with recent … Zero-Click AI Attack Chains Bypass Human Oversight in Agentic SystemsRead more
This Crucial Anthropic Bug Lets Criminals Steal Code: Inside the Silent Claude Code Sandbox Bypass
AI firm Anthropic is facing intense scrutiny from the cybersecurity community after quietly patching a second … This Crucial Anthropic Bug Lets Criminals Steal Code: Inside the Silent Claude Code Sandbox BypassRead more
Mitigating OpenClaw Vulnerabilities: A Guide to AI Agent Security
The rapid adoption of Autonomous AI agents has introduced a new frontier for cyberattacks. Recently, researchers … Mitigating OpenClaw Vulnerabilities: A Guide to AI Agent SecurityRead more
Gemini CLI Vulnerability Enables CI/CD Code Execution
As AI tools become deeply integrated into software development workflows, they are also becoming part of … Gemini CLI Vulnerability Enables CI/CD Code ExecutionRead more
The AI Privacy Alarm: Claude Desktop’s Silent Manifest Deployment
In the race to build “agentic” AI—tools that can act on your behalf across digital environments—transparency … The AI Privacy Alarm: Claude Desktop’s Silent Manifest DeploymentRead more
GPT-5.5 Bio Bug Bounty Targets AI Safety Risks
As AI systems become more capable, the risks are no longer limited to hallucinations or data … GPT-5.5 Bio Bug Bounty Targets AI Safety RisksRead more
GitHub AI Agents Hit by Prompt Injection via Comments
A new class of AI security vulnerability is redefining how attackers compromise development pipelines. Dubbed “Comment … GitHub AI Agents Hit by Prompt Injection via CommentsRead more