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
Prompt Injection
💉 Prompt Injection
Specific
Prompt injection attacks on LLMs
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
504
posts in
8.3
ms
Mathematical proof reveals why fixed
AI
guardrails can never block every
jailbreak
🛡️
AI Security
techxplore.com
·
2d
2 days ago
Actions for Mathematical proof reveals why fixed AI guardrails can never block every jailbreak
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
iOS 27 Security: What WWDC 2026’s
AI
Features Mean for Mobile App Risk
🪄
Prompt Engineering
Content type:
Blog
nowsecure.com
·
1d
1 day ago
Actions for iOS 27 Security: What WWDC 2026’s AI Features Mean for Mobile App Risk
Less-relevant results
Stop putting everything in context: how to reduce agentic coding cost at scale
🪄
Prompt Engineering
simon-free.github.io
·
22h
22 hours ago
·
Hacker News
Actions for Stop putting everything in context: how to reduce agentic coding cost at scale
Prompt
Injection
in RAG Agentic
Systems
🪄
Prompt Engineering
ulad.net
·
5d
5 days ago
·
Hacker News
Actions for Prompt Injection in RAG Agentic Systems
Amazon Locking Down 10th Gen Kindles with New Software Update
🔓
Open Source Software
Content type:
Blog
blog.the-ebook-reader.com
·
17h
17 hours ago
Actions for Amazon Locking Down 10th Gen Kindles with New Software Update
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
OpenAI adds Lockdown
Mode
to ChatGPT to block data theft from
prompt
injection
attacks
🪄
Prompt Engineering
Content type:
News
thenextweb.com
·
6d
6 days ago
·
Cited by 1 article
Actions for OpenAI adds Lockdown Mode to ChatGPT to block data theft from prompt injection attacks
Shai-Hulud Campaign Evolution: Miasma, Hades, and
AI
Scanner Evasion
🔓
Open Source Software
malware.news
·
18h
18 hours ago
Actions for Shai-Hulud Campaign Evolution: Miasma, Hades, and AI Scanner Evasion
Managing
AI
Chat History — Part II: From Naive Storage to Intelligent Memory
🪄
Prompt Engineering
Content type:
Blog
thefrugaltechie.medium.com
·
2d
2 days ago
Actions for Managing AI Chat History — Part II: From Naive Storage to Intelligent Memory
iOS 27
system
prompts
🪄
Prompt Engineering
gist.github.com
·
3d
3 days ago
·
Lobsters
,
Hacker News
·
Cited by 1 article
Actions for iOS 27 system prompts
Claude Powered Code Review that scales!
🪄
Prompt Engineering
Content type:
Blog
medium.com
·
2d
2 days ago
Actions for Claude Powered Code Review that scales!
Building and evaluating
model
diffing agents
🪄
Prompt Engineering
lesswrong.com
·
22h
22 hours ago
Actions for Building and evaluating model diffing agents
Guardian Runtime – Local firewall for
AI
coding agents and runaway costs
👨💻
AI Coding
pypi.org
·
1d
1 day ago
·
Hacker News
·
Cited by 1 article
Actions for Guardian Runtime – Local firewall for AI coding agents and runaway costs
Inside ChatGPT’s New Lockdown
Mode
: Is Your Data
Safer
?
🪄
Prompt Engineering
telecomtalk.info
·
5d
5 days ago
Actions for Inside ChatGPT’s New Lockdown Mode: Is Your Data Safer?
How Anthropic most Advance
Model
Fable 5(Mythos) was jailbroken within…
🪄
Prompt Engineering
Content type:
Blog
medium.com
·
2d
2 days ago
Actions for How Anthropic most Advance Model Fable 5(Mythos) was jailbroken within…
RoboHack
AI
CTF (Robotic Hacking Community at DEFCON 34)
🛡️
AI Security
ctftime.org
·
3d
3 days ago
Actions for RoboHack AI CTF (Robotic Hacking Community at DEFCON 34)
US limits use of Anthropic
AI
models
Fable 5 and Mythos
🛡️
AI Security
Content type:
News
semafor.com
·
11h
11 hours ago
·
Cited by 3 articles
Actions for US limits use of Anthropic AI models Fable 5 and Mythos
Six levels, one lesson:
LLMs
cannot keep a secret
🪄
Prompt Engineering
infosecwriteups.com
·
1d
1 day ago
Actions for Six levels, one lesson: LLMs cannot keep a secret
microsoft/LLMLingua
: [EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the
prompt
and KV-Cache, which achieves up to 20x compression with minimal performance loss.
🤖
LLMs
Content type:
Code
github.com
·
11h
11 hours ago
·
DEV
Actions for microsoft/LLMLingua: [EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Sign up or log in to see more results
Sign Up
Login
« Page 2
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