Where AI Systems Leak Data: A Lifecycle Review of Real Exposure Paths
Praetorian research maps real data exposure paths throughout AI system lifecycles, from training data leakage to operational logging vulnerabilities.
Read more →Security News
Latest cybersecurity news, vulnerabilities, and threat intelligence
Weaponizing Apple AI for Offensive Operations: MLArc C2 Framework
Security researcher hxr1 introduces MLArc, a C2 framework weaponizing Apple CoreML and Vision AI frameworks for covert offensive operations on macOS.
Read more →
Turning AI Safeguards Into Weapons: HITL Dialog Forging Attack
Checkmarx discovers HITL Dialog Forging attack that weaponizes human-in-the-loop AI safeguards by manipulating approval dialogs for malicious actions.
Read more →
Threat Actors Actively Targeting LLMs: GreyNoise Observes Attack Surge
GreyNoise detects surge in threat actors targeting LLM infrastructure, probing for vulnerabilities in model endpoints and AI deployment frameworks.
Read more →
Remote Code Execution in Modern AI/ML Formats and Libraries
Unit42 discloses RCE vulnerabilities in NVIDIA NeMo, Salesforce, and FlexTok AI libraries through unsafe model configuration deserialization.
Read more →
Pwning Claude Code: Researchers Discover Eight Attack Vectors
Flatt Security research reveals eight attack vectors against Claude Code CLI, demonstrating prompt injection and command execution vulnerabilities.
Read more →
OWASP Agentic AI Top 10: Critical Threats Emerge in the Wild
Lares Labs analysis reveals OWASP Agentic AI Top 10 threats are actively exploited in the wild, from goal hijacking to cascading multi-agent failures.
Read more →
The Map Is Not the Territory: Understanding Agent Tool Trust Boundaries
Niyikiza research explores AI agent tool trust boundary gaps where tool descriptions diverge from actual capabilities, creating exploitable security vulnerabilities.
Read more →
IBM AI Agent Bob Manipulated to Download and Execute Malware
PromptArmor researchers demonstrate IBM AI coding agent Bob can be manipulated to download and execute malware through prompt injection vulnerabilities.
Read more →
Inside GoBruteforcer: AI-Generated Server Defaults Power Crypto Campaigns
Check Point exposes GoBruteforcer malware using AI-generated credential lists to compromise servers for cryptocurrency mining operations.
Read more →