AI Security

Feeds to Scour
SubscribedAll
Scoured 85 posts in 4.2 ms

Securing AI Systems: Red Teaming, Prompt Injection, and Adversarial Testing

 🛡️Guardrails  Content type: Blog
dev.to··DEV

Assessing Automated Prompt Injection Attacks in Agentic Environments

 🛡️Guardrails  Content type: Academic
arxiv.org·
Less-relevant results

Siri AI is a Malware Vector

 🛡️Guardrails  Content type: Blog
loufranco.com··Hacker News

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks

 🛡️Guardrails

PuskesmasAI: Finishing an Offline AI Triage App for Rural Indonesia

 🛡️Guardrails  Content type: Code
github.com··DEV

How to Defend Against Prompt Injection in Production

 🧠LLMs  Content type: Reference
leanpub.com··DEV

Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets

 🛡️Guardrails  Content type: Blog
varonis.com··Hacker News

Prompt Injection in RAG Agentic Systems

 🔍RAG
ulad.net··Hacker News

Meta’s AI Support Hack Is a Warning for Every Team Automating User Access

 🛡️Guardrails  Content type: Discussion
langprotect.com··DEV

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

 🛡️Guardrails
trendmicro.com··Hacker News

New Attacks Trick OpenClaw AI Agent Into Running Code and Leaking Secrets

 🛡️Guardrails
thehackernews.com··DEV

Google ADK Security: 5 Layers That Defend AI Agents From Prompt Injection

 🛡️Guardrails  Content type: Blog
dev.to··DEV

Polymarket Annotation Injection

 🛡️Guardrails

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

 🛡️Guardrails  Content type: Academic
arxiv.org·

ShadowFeed Weekly #1: IronWorm npm Attack, $36M Humanity Protocol Hack, Microsoft Repos Compromised

 🛡️Guardrails
x.com··DEV

Claude on Google Cloud: Monitoring and Securing Agents at Scale

 🛡️Guardrails
anthropic.com·

Miasma Worm Hits Microsoft Again: Azure Functions Action and 72 Other Repositories Disabled After Supply Chain Attack Targeting AI Coding Agents

 🛡️Guardrails  Content type: Blog

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

 🎼Agent Orchestration  Content type: News

Claude Fable is relentlessly proactive

 🛡️Guardrails
simonwillison.net··Hacker News

I Made Two AI Models Fight Each Other. They Agreed Way Too Much.

 🛡️Guardrails  Content type: Blog
dev.to··DEV

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