Guardrails

Feeds to Scour
SubscribedAll
Scoured 111 posts in 12.7 ms

JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

How to Defend Against Prompt Injection in Production

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

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

 🌐Open Source AI  Content type: Blog
dev.to··DEV

Anthropic's Fable Jailbreak (Circumvent safety nets)

 ✍️Prompt Engineering  Content type: Code
github.com··Hacker News

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

 🔐AI Security  Content type: Discussion
langprotect.com··DEV

AdBreak – Jailbreaking the Kindle

 🔐AI Security
kindlemodding.org··Hacker News
Less-relevant results

iOS Security SDKs & Audits for Production Teams

 🔐AI Security  Content type: Discussion
sentinelden.com··Hacker News

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

 🔐AI Security
techcrunch.com··Hacker News

AI researcher claims he's bypassed Anthropic's Fable 5 guardrails

 🔐AI Security
cointelegraph.com··Hacker News

Prompt Injection in RAG Agentic Systems

 🔍RAG
ulad.net··Hacker News

Siri AI is a Malware Vector

 🔐AI Security  Content type: Blog
loufranco.com··Hacker News

Polymarket Annotation Injection

 🔐AI Security
sam.elborai.me··Hacker News

Anthropic makes Fable 5's invisible safeguards visible after backlash

 ✍️Prompt Engineering
xcancel.com··Hacker News

Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets

 🔐AI Security  Content type: Blog
varonis.com··Hacker News

The Meta hack shows there’s more to AI security than Mythos

 🔐AI Security  Content type: News
technologyreview.com··Hacker News

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

 🔐AI Security
thehackernews.com··DEV

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

 🔐AI Security  Content type: Blog
dev.to··DEV

Breaking LiteLLM: From Low-Privilege User to Admin and RCE (CVE-2026-47101, CVE-2026-47102, CVE-2026-40217)

 🌐Open Source AI  Content type: Blog
obsidiansecurity.com··Hacker News

Assessing Automated Prompt Injection Attacks in Agentic Environments

 🔐AI Security  Content type: Academic
arxiv.org·

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

 🔐AI Security
trendmicro.com··Hacker News

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