Tagged "security"
-
French Legal Profession Mandates Open-Source AI for Confidential Data – Policy Shift Toward Local Models
-
DEF CON 34 Exposes 10 Critical Vulnerabilities in Local AI Systems
-
llama.cpp Adds Tool Isolation Support via Docker
-
SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems
-
Ask HN: What are your rules for letting an AI agent commit code?
-
Anthropic Says Its AI Systems Broke into Computers at 3 Organizations
-
Tether Data Releases VisionPsy-Nano: Open Source Edge Visual Language Model
-
NightRun UEFI Application Boots Local LLM on Raspberry Pi 5 and x86 PCs Without an OS
-
Anthropic Secures Its AI-Native Software Development Lifecycle
-
Ruff v0.16.0: 413 Default Rules for Code Quality in AI Development
-
Don't Buy an Uncensored AI on a Flash Drive: What You Can Do Instead
-
OpenAI Says Its A.I. Models Went Rogue and Attacked a Digital Library
-
Keyline: Securely Share .env Files Without Leaving Your Laptop
-
On-Device AI That Respects Your Privacy Gains Traction
-
Bringing Up the RK3576 NPU on Mainline Linux: A Byte-Exact Single-Task Path
-
Vivo Unveils Security Solution for On-Device AI at AI for Good Global Summit 2026
-
Runeward: Sandboxing AI Agents with Policy Gates
-
A Font That Humans Can Read But AI Cannot
-
CorvinOS – Self-Hosted OS for AI Agents with Compliance Built Into Runtime
-
Show HN: Chat Privacy – Hide AI Chat History While Screen Sharing
-
Show HN: Tarit – Self-host Sandbox Cloud and Hypervisor for AI Agents
-
I Gave My Local LLM Email Access Without Handing Over My Entire Inbox
-
Critical GPU Memory Leak Vulnerability Discovered in vLLM
-
Show HN: Kiwi – Run Agentic Dev Loops in the Cloud, Keep Keys on Your Laptop
-
NIS2 Compliance Drives European Office Software Toward Local AI Solutions
-
Bounding the Blast Radius: A Survey of Prompt-Injection Defenses for LLM Agents
-
code-on-incus: Isolated Machine Environments for AI Agents
-
WebBrain: Open-Source Local AI Browser Agent for Task Automation
-
The Cloud Has an Address: Why Data Center Resilience Matters for Local Inference
-
Ask HN: How do you provide your AI agents with access to credentials/secrets?
-
Reachy Mini Adds Local Conversational AI
-
Show HN: NetSentinel – a local network security scanner and connectivity monitor
-
Hermes Agent Framework Extends Local LLMs with Script and Job Execution
-
Two-Tier Local AI Architecture Keeps Sensitive Data Offline
-
Chrome Downloads 4GB AI Model: Implications for Local On-Device AI
-
Show HN: SpadeBox – Sandboxed tools and JavaScript runtime for AI agents
-
Outpost – Capability-based API access for AI agents
-
Due to DMA, Siri AI Delayed in EU for iOS 27 and iPadOS 27
-
DockSec: Open-Source AI-Powered Container Security Scanner for Self-Hosted Deployments
-
Pizx – zx and Pi AI = shell scripting with 15 AI agent patterns
-
A New YC Tool Promises "Your Code Never Leaves Your Machine." It Does
-
Show HN: Akmon, Verify What an AI Agent Did Offline Using Only OpenSSL
-
South Korea Finalizes $520 Million Budget for On-Device AI Chip Development Program
-
NVIDIA Joins Windows on Arm Ecosystem, Driving Arm-Based AI Notebook Adoption to 34.2% by 2029
-
NanoClaw Founder on OpenClaw's Security Issues: 800k Lines of Code, Sloppiness and Poor Security
-
Supply Chain DLP: Stop Leaked .env Files, Credentials, SSH Keys, and API Tokens
-
NVIDIA and Microsoft Team Up to Bring Secure On-Device AI Agents to Windows PCs
-
Chrome Quietly Downloads 4GB AI Model for Local Processing
-
Proveyouragent: Cryptographic Identity for AI Agents (Ed25519 and DPoP)
-
Show HN: Egress WAF to Limit AI Agents and NPM Malware Based on mitmproxy
-
Apple Doubles Down on On-Device AI at WWDC 2026, Setting Privacy-First Strategy
-
Privacy-Focused Raspberry Pi Zero 2W DIY Security Camera with On-Device AI and End-to-End Encryption
-
MCP Security Flaws Are Turning AI Infrastructure Into a Supply-Chain Risk
-
llama.cpp GGUF Parser Flaws: Critical Integer Overflow Enables Arbitrary Reads in Every Local AI Stack
-
AI Guardrails Stripped From Meta and Google Models in Minutes
-
Developer Builds Local AI Coding Setup with Editor Integration, Zero Cloud Dependency
-
Nvidia Raises Video Encoder Limit to 12 on Consumer GPUs
-
Auditing Apple's DifferentialPrivacy.framework: Bugs, Misconfig, Practical Risks
-
eXo MCP Server Enables Secure AI Agent Access to Workplace Tools
-
Ansede-static: Offline SAST Tool Demonstrates Value of Local AI Tools
-
Local LLM Takes Control of Video Doorbell—The Future of Smart Cameras
-
AI, open code and vulnerability risk in the public sector
-
Critical Out-of-Bounds Read Vulnerability Discovered in Ollama
-
Claude Opus 4.7 System Prompt Leaks Raise Local Deployment Questions
-
Researchers Report AI Breaking Every Benchmark for Autonomous Cyber Capability
-
Mass NPM Supply Chain Attack Hits TanStack, Mistral AI, and 170 Packages
-
Ollama Vulnerability Exposes Remote Process Memory
-
Ollama Out-of-Bounds Read Vulnerability Allows Remote Process Memory Leak
-
Claude Code with Local LLM Running Offline: The Hybrid Setup You Didn't Know You Needed
-
Critical Ollama Memory Leak Vulnerability Exposes 300,000 Servers Globally
-
0ctx – Local-First Project Memory for AI Workflows
-
Google Removes Privacy Assurances After Stuffing Devices With Their AI Model
-
Show HN: Runs AI Coding Agents Inside Isolated Docker Containers
-
Critical Ollama Memory Leak Vulnerability Exposes 300,000 Servers Globally
-
I got prompt-injected asking Claude on iOS to recommend a cycling route app
-
Critical Ollama Memory Leak Vulnerability Exposes 300,000 Servers Globally
-
Enterprise Workplace AI: Questions on Standardizing Local vs Cloud Models
-
NHS England Withdraws AI Software Over Security and Hacking Concerns
-
Critical Security Vulnerabilities in Ollama Auto-Updater Enable Remote Code Execution
-
US State Dept Orders Global Warning About Alleged AI Thefts by DeepSeek
-
NHS to Close-Source GitHub Repos Over AI and Security Concerns
-
NordVPN Adds On-Device AI Voice Detector to Chrome Extension to Identify Synthetic Audio
-
Control AI Risk with Pre-Built Frameworks and Ready-to-Run Evaluations
-
Home Assistant's Local LLM Support Outperforms Gemini for Home Automation
-
Show HN: Minimal Linux Sandboxes to Manage AI-Generated Code with Ease
-
Thinking Outside the Box: New Attack Surfaces in Sandboxed AI Agents
-
SiGit Code: Local-First Coding Agent
-
Critical Security Flaw: Hackers Can Exploit Ollama Model Uploads to Leak Sensitive Server Data
-
Hackers Exploit Ollama Model Uploads to Leak Server Data
-
Local LLM for Private Companies
-
Cortex Auth – Rust secrets vault for AI agents (exec-based injection)
-
Malicious GGUF Models Could Trigger Remote Code Execution on SGLang Servers
-
Build a More Secure, Always-On Local AI Agent with OpenClaw and NVIDIA NemoClaw
-
Exposed LLM Infrastructure: How Attackers Find and Exploit Misconfigured AI Deployments
-
The Case for Out-of-Process Enforcement for AI Agents
-
Building Practical Local Coding Assistants: A Working Stack for Editor Integration
-
Developer Shares Golden Stack for Local Coding Assistant Integration Directly Inside Code Editors
-
Ubiquiti UniFi G6 Turret 4K Camera Features On-Device AI Processing at $199 Price Point
-
Defender – Local Prompt Injection Detection for AI Agents
-
On-Device AI Inference Emerges as New Security Blind Spot for CISOs
-
I Gave My AI Shell Access and Felt Uneasy – So I Sandboxed It
-
On-Device Apple Intelligence Vulnerable to Prompt Injection Attacks
-
Local Small LLMs Match Enterprise Model Performance on Vulnerability Detection
-
Hugging Face Moves Safetensors Under PyTorch Foundation
-
Privilege Escalation Attacks on GPUs Using Rowhammer
-
METATRON: Open-Source AI Penetration Testing with Local LLMs
-
If Your AI Agent Ran NPM Install During the Axios Attack, You're Compromised
-
Miasma: A Tool to Protect Data from AI Web Scrapers
-
Prompt Security Challenges Emerge as Critical Concern for Local LLM Deployments
-
Why Your AI Agents Will Turn Against You
-
Critical: LiteLLM Supply Chain Attack Detected, Bifrost Alternative Released
-
South Korea Science Ministry Seeks Five On-Device AI Pilot Projects for Public Services
-
Self-Hosted AI Code Review with Local LLMs: Secure Automation Guide
-
SwarmHawk – Open-Source CLI for Vulnerability Scanning with AI Synthesis
-
Cybersecurity Skills for AI Agents – agentskills.io Standard Implementation
-
Claude Code Permissions Hook – Delegate Permission Approval to LLM
-
LucidShark – Local-first, open-source quality and security gate
-
How I Used Lima for an AI Coding Agent Sandbox
-
Researcher Discovers Universal "Danger Zone" in Transformer Model Architecture at 50% Depth
-
How AI Agents Should Pay for API Calls: X402 and USDC Verification on Base
-
AgentArmor: Open-Source 8-Layer Security Framework for AI Agents
-
Local AI Coding Assistant: Complete VS Code + Ollama + Continue Setup
-
Researchers Gave AI Agents Real Tools. One Deleted Its Own Mail Server
-
Kali Linux Integrates Local Ollama and MCP for AI-Driven Penetration Testing
-
Gyro-Claw – Secure Execution Runtime for AI Agents
-
Show HN: SimplAI – Build and Deploy AI Agents and Workflows Without Boilerplate
-
Show HN: RedDragon – LLM-Assisted IR Analysis of Code Across Languages
-
Imrobot – Reverse-CAPTCHA for Verifying AI Agents, Not Humans
-
Galaxy S26 Debuts AI-Powered Scam Detection in Bold Security Push
-
We Audited the Security of 7 Open-Source AI Agents – Here Is What We Found
-
Show HN: Anonymize LLM traffic to dodge API fingerprinting and rate-limiting
-
Every agent framework has the same bug – prompt decay. Here's a fix
-
Anthropic Reveals Industrial-Scale Distillation Attacks by Chinese AI Labs
-
Show HN: A Ground Up TLS 1.3 Client Written in C
-
Massu: Governance Layer for AI Coding Assistants with 51 MCP Tools
-
Security Alert: Fraudulent Shade Software Plagiarized from Heretic Project
-
Mihup and Qualcomm Collaborate to Advance Secure On-Device Voice AI for BFSI
-
Clipthesis: Free Local App for Video Tagging and Search Across Drives
-
Aegis.rs: Open Source Rust-Based LLM Security Proxy Released
-
Tailscale Releases New Tool to Prevent Sensitive Data Leakage to Cloud AI Services
-
I attacked my own LangGraph agent system. All 6 attacks worked
-
Show HN: Inkog – Pre-flight check for AI agents (governance, loops, injection)
-
I broke into my own AI system in 10 minutes. I built it
-
Security Alert: Open Claw Designed for Self-Hosting, Stop Sharing Credentials
-
Critical vLLM RCE Vulnerability Allows Remote Code Execution via Video Links
-
175,000 Publicly Exposed Ollama AI Servers Discovered Across 130 Countries
-
5 Practical Ways to Use Local LLMs with MCP Tools