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
LLM safety
🛡 LLM safety
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
377
posts in
23.3
ms
Zero-Click IP Leak in a Privacy Search Engine: Indirect
Prompt
Injection
& Silent Patching
🛡️
Red Teaming
infosecwriteups.com
·
2d
2 days ago
Actions for Zero-Click IP Leak in a Privacy Search Engine: Indirect Prompt Injection & Silent Patching
Claude Fable 5: The "
Safe
" Mythos for Everyone
🛡️
Red Teaming
drkpxl.com
·
2h
2 hours ago
Actions for Claude Fable 5: The "Safe" Mythos for Everyone
Your
AI
Agent Can Read. That’s the Whole Problem.
🛡️
Red Teaming
Content type:
Blog
medium.com
·
6d
6 days ago
Actions for Your AI Agent Can Read. That’s the Whole Problem.
Prompt
injection
still drives most agentic
AI
security failures in production
🛡️
Red Teaming
helpnetsecurity.com
·
15h
15 hours ago
Actions for Prompt injection still drives most agentic AI security failures in production
How I Gave My Security Blog Its Own
AI
Agent and an Attitude
🛡️
Red Teaming
Content type:
Blog
medium.com
·
2d
2 days ago
Actions for How I Gave My Security Blog Its Own AI Agent and an Attitude
When Your
AI
Agent’s Memory Becomes a Security Liability
🤖
Agent Architectures
Content type:
News
Content type:
Blog
blog.checkpoint.com
·
14h
14 hours ago
Actions for When Your AI Agent’s Memory Becomes a Security Liability
Autonomous Pentesting vs Autonomous
Red
Teaming
: What's the Difference?
🛡️
Red Teaming
malware.news
·
4d
4 days ago
Actions for Autonomous Pentesting vs Autonomous Red Teaming: What's the Difference?
Claude Code vulnerability exposes developer credentials via
prompt
injection
⚙
Automation
4sysops.com
·
1d
1 day ago
Actions for Claude Code vulnerability exposes developer credentials via prompt injection
Trust No Skill: Integrity Verification for
AI
Agent Supply Chains
🛡️
Red Teaming
Content type:
Blog
unit42.paloaltonetworks.com
·
20h
20 hours ago
Actions for Trust No Skill: Integrity Verification for AI Agent Supply Chains
[Recorded talk] "
AI
Alignment
Versus
AI
Ethical Treatment: 10 Challenges"
🎯
AI Alignment
Content type:
Blog
meditationsondigitalminds.substack.com
·
2d
2 days ago
·
Substack
Actions for [Recorded talk] "AI Alignment Versus AI Ethical Treatment: 10 Challenges"
ChatGPT's new Lockdown
Mode
lets you disable web access and more to protect sensitive data from
prompt
injection
🛡️
Red Teaming
the-decoder.com
·
4d
4 days ago
Actions for ChatGPT's new Lockdown Mode lets you disable web access and more to protect sensitive data from prompt injection
JailbreakOPT
: Tool-Assisted Iterative Jailbreak
Prompt
Optimization
🛡️
Red Teaming
Content type:
Academic
arxiv.org
·
16h
16 hours ago
Actions for JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization
Security Flaw in Claude Code Illustrates the Risk of
AI
in Developer Workflows
⚙
Automation
devops.com
·
1d
1 day ago
Actions for Security Flaw in Claude Code Illustrates the Risk of AI in Developer Workflows
Guardian Angels:
LLM
Personalization for Productivity and Security
🎯
AI Alignment
gwern.net
·
4d
4 days ago
·
Hacker News
Actions for Guardian Angels: LLM Personalization for Productivity and Security
ashp15205/guardian-runtime: A zero-latency, local-first runtime firewall for LLMs. Intercept every
prompt
and response locally to stop data leaks and runaway token costs.
💭
Context Management
Content type:
Code
github.com
·
2d
2 days ago
·
Hacker News
,
Hacker News
Actions for ashp15205/guardian-runtime: A zero-latency, local-first runtime firewall for LLMs. Intercept every prompt and response locally to stop data leaks and runaway token costs.
AI
researcher claims he's bypassed Anthropic's Fable 5 guardrails
🛡️
Red Teaming
cointelegraph.com
·
14h
14 hours ago
·
Hacker News
Actions for AI researcher claims he's bypassed Anthropic's Fable 5 guardrails
OpenAI adds Lockdown
Mode
to ChatGPT to block data theft from
prompt
injection
attacks
🛡️
Red Teaming
Content type:
News
thenextweb.com
·
4d
4 days ago
Actions for OpenAI adds Lockdown Mode to ChatGPT to block data theft from prompt injection attacks
Anthropic makes Fable 5's invisible safeguards visible after backlash
🛡️
Red Teaming
xcancel.com
·
12h
12 hours ago
·
Hacker News
Actions for Anthropic makes Fable 5's invisible safeguards visible after backlash
Meet Hades: The malware that lies to
AI
security agents
✍️
Prompt Engineering
Content type:
News
infoworld.com
·
2d
2 days ago
·
Hacker News
Actions for Meet Hades: The malware that lies to AI security agents
Indirect
Prompt
Injection
remains a fundamental security challenge for
AI
🛡️
Red Teaming
Content type:
Blog
brave.com
·
3d
3 days ago
Actions for Indirect Prompt Injection remains a fundamental security challenge for AI
« 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