AI Security

Feeds to Scour
SubscribedAll
Scoured 209 posts in 12.2 ms

Every set of AI guardrails can be broken by the right prompt

 🔒Cybersecurity
helpnetsecurity.com·

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

 🔐Hardware Security
thehackernews.com·

Google DeepMind is worried about what happens when millions of agents start to interact

 🔒Cybersecurity  Content type: News
technologyreview.com··Hacker News

OpenAI rolls out a Lockdown Mode for extra protection against prompt injection attacks

 🔐Hardware Security  Content type: News
engadget.com·

What it looks like: Trusted, compliant AI systems at scale - Azure AI Tech Accelerator

 🛡️Security Type Systems
techcommunity.microsoft.com·

Reconstructing AI activity in investigations

 🎯Threat Intelligence
malware.news·

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

 🔐Hardware Security
indiehacker.news·

Pwning Agentic AI Part I: Your AI Agent Is Already Compromised

 🔒Cybersecurity
trendmicro.com··Hacker News

AI Security Newsletter -⁠ May 2026

 🛡️Computer Security  Content type: Blog
medium.com
·

Infosec News Nuggets — June 9, 2026

 🔒Cybersecurity
aboutdfir.com·

How ChatGPT's new Lockdown mode protects you from data theft (and what else it does)

 🔐Hardware Security  Content type: News
zdnet.com·

Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets

 🔒Cybersecurity  Content type: Blog
varonis.com··Hacker News

ChatGPT Introduces Lockdown Mode to Everyone, Preventing Prompt Injection Attacks

 🔐Hardware Security
researchsnipers.com·

The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection

 🎯Threat Intelligence  Content type: Academic
arxiv.org·

New “Agentjacking” Attacks Could Hijack AI Coding Agents

 🔒Cybersecurity  Content type: News
infosecurity-magazine.com·

# I Spent 6 Hours Hacking Coinbase-Backed Bankr. Here’s Everything I Found.

 🔓Binary Exploitation  Content type: Blog
medium.com
·

agentsploit/agentsploit: Offensive security framework for AI agents and MCP servers.

 🔓Binary Exploitation  Content type: Code
github.com··Hacker News

Prompt Injection in RAG Agentic Systems

 🛡️Security Type Systems
ulad.net··Hacker News

OpenAI’s Lockdown Mode is trying to solve the problem that it created

 🔒Cybersecurity  Content type: News
csoonline.com·

The Practitioner’s Guide to AgentOps

 🎯Threat Intelligence
machinelearningmastery.com·
Sign up or log in to see more results
Sign UpLogin

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help