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
Model Poisoning, Adversarial Examples, Prompt Injection, AI Safety
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
353
posts in
8.0
ms
Malware uses fake nuclear weapon
prompts
to bypass
AI
security
scanners
🪄
Prompt Engineering
4sysops.com
·
22h
22 hours ago
Actions for Malware uses fake nuclear weapon prompts to bypass AI security scanners
WebMCP Can Be Used To Hijack
AI
Agents, Chrome Warns via @sejournal, @martinibuster
🪄
Prompt Engineering
searchenginejournal.com
·
2d
2 days ago
Actions for WebMCP Can Be Used To Hijack AI Agents, Chrome Warns via @sejournal, @martinibuster
Advanced
AI
Safety
Addendum
👨💻
AI Coding
cloud.google.com
·
3d
3 days ago
·
Hacker News
Actions for Advanced AI Safety Addendum
Singapore deepens
AI
safety
push with IMDA-Microsoft partnership
👨💻
AI Coding
channelnewsasia.com
·
1d
1 day ago
Actions for Singapore deepens AI safety push with IMDA-Microsoft partnership
How to Defend Against
Prompt
Injection
in Production
🪄
Prompt Engineering
Content type:
Reference
leanpub.com
·
4d
4 days ago
·
DEV
Actions for How to Defend Against Prompt Injection in Production
Prompt
injection
still drives most agentic
AI
security failures in production
🪄
Prompt Engineering
helpnetsecurity.com
·
2d
2 days ago
Actions for Prompt injection still drives most agentic AI security failures in production
Prompt
injection
breaks today’s
AI
agents, study warns
🪄
Prompt Engineering
Content type:
News
csoonline.com
·
1d
1 day ago
Actions for Prompt injection breaks today’s AI agents, study warns
OpenAI unveils Lockdown
Mode
to protect sensitive data from
prompt
injection
attacks
🪄
Prompt Engineering
6
articles covering this post
techcrunch.com
·
6d
6 days ago
·
Hacker News
·
Cited by 6 articles
Actions for OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
Short Timelines Favor Control, Long Timelines Favor Infrastructure
Security
🪄
Prompt Engineering
lesswrong.com
·
13h
13 hours ago
Actions for Short Timelines Favor Control, Long Timelines Favor Infrastructure Security
Security
Flaw in Claude Code Illustrates the Risk of
AI
in Developer Workflows
🪄
Prompt Engineering
devops.com
·
2d
2 days ago
Actions for Security Flaw in Claude Code Illustrates the Risk of AI in Developer Workflows
ChatGPT can be hijacked without you knowing. Lockdown
Mode
is the fix
🪄
Prompt Engineering
Content type:
News
pcworld.com
·
3d
3 days ago
Actions for ChatGPT can be hijacked without you knowing. Lockdown Mode is the fix
After
AI
Safety
Certification- Why
Model
Safety
Does Not Solve the Authority Problem
👨💻
AI Coding
Content type:
Blog
medium.com
·
10h
10 hours ago
Actions for After AI Safety Certification- Why Model Safety Does Not Solve the Authority Problem
Claude Code vulnerability exposes developer credentials via
prompt
injection
🪄
Prompt Engineering
4sysops.com
·
2d
2 days ago
Actions for Claude Code vulnerability exposes developer credentials via prompt injection
ChatGPT's new Lockdown
Mode
lets you disable web access and more to protect sensitive data from
prompt
injection
🪄
Prompt Engineering
the-decoder.com
·
6d
6 days ago
Actions for ChatGPT's new Lockdown Mode lets you disable web access and more to protect sensitive data from prompt injection
Configure input guardrails for an OpenShift
AI
voice agent
🪄
Prompt Engineering
developers.redhat.com
·
2d
2 days ago
Actions for Configure input guardrails for an OpenShift AI voice agent
Like US
models
, Chinese
AI
is learning to ‘game’
safety
tests, research lab says
🤖
AI
Content type:
News
scmp.com
·
7h
7 hours ago
Actions for Like US models, Chinese AI is learning to ‘game’ safety tests, research lab says
My Oslo Freedom Forum Keynote: Authoritarians and
AI
🤖
AI
Content type:
Blog
redpacket.substack.com
·
4d
4 days ago
·
Substack
Actions for My Oslo Freedom Forum Keynote: Authoritarians and AI
xAI fired an engineer who raised alarms about Grok
safety
, new lawsuit claims
🪄
Prompt Engineering
6
articles covering this post
techcrunch.com
·
2d
2 days ago
·
Cited by 6 articles
Actions for xAI fired an engineer who raised alarms about Grok safety, new lawsuit claims
Why Anthropic’s Latest
AI
Safety
Controversy Matters More Than Most People Realize
🪄
Prompt Engineering
Content type:
Blog
medium.com
·
9h
9 hours ago
Actions for Why Anthropic’s Latest AI Safety Controversy Matters More Than Most People Realize
The Anthropic Incident and the Shift from
AI
Safety
to Authority Governance
🤖
AI
Content type:
Blog
medium.com
·
1h
1 hour ago
Actions for The Anthropic Incident and the Shift from AI Safety to Authority Governance
« 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