🛡️ AI Security - moznotes · Scour

Prompt Injection in RAG Agentic Systems

🧠LLM Engineering

ulad.net··Hacker News

Indirect Prompt Injection remains a fundamental security challenge for AI

🍎Apple Blog

Inside ChatGPT’s New Lockdown Mode: Is Your Data Safer?

🛠️Product Security

telecomtalk.info·

Assessing Automated Prompt Injection Attacks in Agentic Environments

⚛️Quantum Security Academic

Your AI Agent Can Read. That’s the Whole Problem.

🛠️Product Security Blog

Zero-Click IP Leak in a Privacy Search Engine: Indirect Prompt Injection & Silent Patching

🛡Cybersecurity

infosecwriteups.com

·

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

🛡Cybersecurity

thehackernews.com·

OpenAI Rolling Out ChatGPT Account Security Controls

🛡Cybersecurity

securityweek.com·

Hackers could use poisoned WhatsApp and Slack notifications to take over your Google Gemini – and make it work on their behalf

🛡Cybersecurity

·

Siri AI is a Malware Vector

🖥️Self-hosted apps Blog

loufranco.com··Hacker News

Apple's AI Can Now Change Your Passwords. What Could Possibly Go Wrong?

🍎Apple Blog

kylereddoch.me··Hacker News

Algebraic Cryptanalytic Extraction on Hard-Label Neural Networks

⚛️Quantum Security

eprint.iacr.org·

#066 - Supabase doubled to $10.5B in 8 months, OpenAI contains prompt injection, Postgres gets durable

🖥️Self-hosted apps

indiehacker.news·

Microsoft releases incident response playbook for Copilot and Azure AI

🛡Cybersecurity

AI Security Newsletter -⁠ May 2026

🛠️Product Security Blog

·

GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines

🔄DevSecOps Academic

Reconstructing AI activity in investigations

🛡Cybersecurity

OpenAI Help: Lockdown Mode

🖥️Self-hosted apps

simonwillison.net·

OpenAI Announces Unnerving New ChatGPT Feature Named ‘Lockdown Mode’

🖥️Self-hosted apps

Infosec News Nuggets — June 9, 2026

🛡Cybersecurity

aboutdfir.com·

Log in to enable infinite scrolling