Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
AI Security
🔐 AI Security
Specific
prompt injection, jailbreak, AI safety, red teaming, threat model
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
192
posts in
114.4
ms
Prompt
injection
still drives most agentic
AI
security failures in production
🤖
AI Agents
helpnetsecurity.com
·
1d
1 day ago
Actions for Prompt injection still drives most agentic AI security failures in production
OpenAI rolls out a Lockdown
Mode
for extra protection against
prompt
injection
attacks
🛡️
Guardrails
Content type:
News
engadget.com
·
6d
6 days ago
Actions for OpenAI rolls out a Lockdown Mode for extra protection against prompt injection attacks
Less-relevant results
iOS 27
Security
: What WWDC 2026’s
AI
Features Mean for Mobile App Risk
🛡️
Guardrails
Content type:
Blog
nowsecure.com
·
18h
18 hours ago
Actions for iOS 27 Security: What WWDC 2026’s AI Features Mean for Mobile App Risk
New ChatGPT Lockdown
Mode
Limits Tools That Could Enable Data Exfiltration
🛡️
Guardrails
thehackernews.com
·
6d
6 days ago
Actions for New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration
Mathematical proof reveals why fixed
AI
guardrails can never block every
jailbreak
🛡️
Guardrails
techxplore.com
·
1d
1 day ago
Actions for Mathematical proof reveals why fixed AI guardrails can never block every jailbreak
How I Gave My
Security
Blog Its Own
AI
Agent and an Attitude
🛡️
Guardrails
Content type:
Blog
medium.com
·
3d
3 days ago
Actions for How I Gave My Security Blog Its Own AI Agent and an Attitude
It's time to update incident response for the
AI
era | TechTarget
🛡️
Guardrails
Content type:
News
techtarget.com
·
6h
6 hours ago
Actions for It's time to update incident response for the AI era | TechTarget
Configure input guardrails for an OpenShift
AI
voice agent
🧠
LLMs
developers.redhat.com
·
1d
1 day ago
Actions for Configure input guardrails for an OpenShift AI voice agent
OpenAI Help: Lockdown
Mode
🛡️
Guardrails
simonwillison.net
·
6d
6 days ago
Actions for OpenAI Help: Lockdown Mode
Microsoft releases incident response playbook for Copilot and Azure
AI
🛡️
Guardrails
4sysops.com
·
2d
2 days ago
Actions for Microsoft releases incident response playbook for Copilot and Azure AI
OpenAI adds Lockdown
Mode
to ChatGPT to block data theft from
prompt
injection
attacks
🛡️
Guardrails
Content type:
News
thenextweb.com
·
5d
5 days ago
Actions for OpenAI adds Lockdown Mode to ChatGPT to block data theft from prompt injection attacks
Who Pays the Price? Stakeholder-Centric
Prompt
Injection
Benchmarking for Real-world Web Agents
🛡️
Guardrails
Content type:
Academic
arxiv.org
·
11h
11 hours ago
Actions for Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents
ChatGPT Introduces Lockdown
Mode
to Everyone, Preventing
Prompt
Injection
Attacks
🛡️
Guardrails
researchsnipers.com
·
6d
6 days ago
Actions for ChatGPT Introduces Lockdown Mode to Everyone, Preventing Prompt Injection Attacks
# I Spent 6 Hours Hacking Coinbase-Backed Bankr. Here’s Everything I Found.
🛡️
Guardrails
Content type:
Blog
medium.com
·
4d
4 days ago
Actions for # I Spent 6 Hours Hacking Coinbase-Backed Bankr. Here’s Everything I Found.
Reconstructing
AI
activity in investigations
🛡️
Guardrails
malware.news
·
2d
2 days ago
Actions for Reconstructing AI activity in investigations
#066 - Supabase doubled to $10.5B in 8 months, OpenAI contains
prompt
injection
, Postgres gets durable
🛡️
Guardrails
indiehacker.news
·
6d
6 days ago
Actions for #066 - Supabase doubled to $10.5B in 8 months, OpenAI contains prompt injection, Postgres gets durable
What it looks like: Trusted, compliant
AI
systems at scale - Azure
AI
Tech Accelerator
🛡️
Guardrails
techcommunity.microsoft.com
·
2d
2 days ago
Actions for What it looks like: Trusted, compliant AI systems at scale - Azure AI Tech Accelerator
OpenAI Announces Unnerving New ChatGPT Feature Named ‘Lockdown
Mode
’
🛡️
Guardrails
gizmodo.com
·
5d
5 days ago
Actions for OpenAI Announces Unnerving New ChatGPT Feature Named ‘Lockdown Mode’
Anthropic releases Mythos-derived
model
with cyber guardrails
🌐
Open Source AI
metacurity.com
·
2d
2 days ago
Actions for Anthropic releases Mythos-derived model with cyber guardrails
How ChatGPT's new Lockdown
mode
protects you from data theft (and what else it does)
🛡️
Guardrails
Content type:
News
zdnet.com
·
4d
4 days ago
Actions for How ChatGPT's new Lockdown mode protects you from data theft (and what else it does)
« Page 1
·
Page 3 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
j
/
k
Open post
o
or
Enter
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
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Browse
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help