Skip to main content
Scour
Discover
Docs
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
LLM Vulnerabilities
🕳 LLM Vulnerabilities
Specific
Hacking LLMs, Prompt Injection
Filter Results
Timeframe
Choose a timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
464
posts in
50.3
ms
🤖
AI
portal.oxlo.ai
·
6d
6 days ago
Overcoming
LLM
Limitations
Covered by
DEV Community
Discussed on
DEV
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Overcoming LLM Limitations
💉
Prompt Injection
arXiv
·
6d
6 days ago
Rapid Poison: Practical Poisoning
Attacks
Against the Rapid Response Framework
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework
🔎
AI Auditing
Check Point Blog
·
5d
5 days ago
AI
Red
Teaming
Makes the Unknowns Known
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for AI Red Teaming Makes the Unknowns Known
🛡️
AI Security
medium.com
·
5d
5 days ago
Why
LLMs
Need a Firewall: Lessons from McDonald’s Two AI Security Failures
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Why LLMs Need a Firewall: Lessons from McDonald’s Two AI Security Failures
🛡️
AI Security
onurcangencbilkent.medium.com
·
6d
6 days ago
AI/ML Security Threats: From Neural Networks to
Prompt
Injection
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for AI/ML Security Threats: From Neural Networks to Prompt Injection
🛡️
AI Security
CSO Online
·
3d
3 days ago
M365 Copilot SearchLeak: Your
prompt
injection
attack
surface just got bigger
Covers
SearchLeak: We Turned M365 Copilot into a One-Click Data Exfiltration Weapon
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for M365 Copilot SearchLeak: Your prompt injection attack surface just got bigger
🛡️
AI Security
Ars Technica
·
6d
6 days ago
Critical Copilot
vulnerability
allowed hackers to seal 2FA code from users
Covers
SearchLeak: We Turned M365 Copilot into a One-Click Data Exfiltration Weapon
Covered by
5 sources
See all sources covering this story
including
Futurism
,
Windows Central
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Critical Copilot vulnerability allowed hackers to seal 2FA code from users
🎭
Claude
LessWrong
·
3d
3 days ago
Claude Fable 5 and Mythos 5: Capabilities
Covers
5 stories
See all stories this covers
including
Claude Fable 5 and Claude Mythos 5
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Claude Fable 5 and Mythos 5: Capabilities
🛡️
AI Security
stefanmiladinovic.medium.com
·
5d
5 days ago
Prompt
Injection
: The Anatomy of an AI
Attack
Flow (And How to Prevent It)
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Prompt Injection: The Anatomy of an AI Attack Flow (And How to Prevent It)
🛡️
AI Security
brevio.pro
·
5d
5 days ago
Show HN: I built 184 free browser tools – PDF, image, dev, AI tasks, no upload
Covered by
indiehacker.news
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Show HN: I built 184 free browser tools – PDF, image, dev, AI tasks, no upload
🤖
Agent Protocols
nmm.ee
·
3d
3 days ago
Do MCP's use more tokens than CLI's?
Covers
Introducing advanced tool use on the Claude Developer Platform
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Do MCP's use more tokens than CLI's?
🎓
Advanced content
lemmy.world
·
6d
6 days ago
Feds freaked over Fable 5 after simple 'fix this code'
prompt
, not
jailbreak
, says researcher
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Feds freaked over Fable 5 after simple 'fix this code' prompt, not jailbreak, says researcher
🛡️
AI Security
OSINT Team Blog
·
3d
3 days ago
The AI
Attack
Surface in 2026 Is Larger Than Most Defenders Realize
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for The AI Attack Surface in 2026 Is Larger Than Most Defenders Realize
🤖
AI
GitHub
·
5d
5 days ago
Pramagent – a trust layer for
LLM
agents (guardrails, tracing, audit)
Covered by
DEV Community
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Pramagent – a trust layer for LLM agents (guardrails, tracing, audit)
🔓
Hacking
youtube.com
Content type:
Video
·
4d
4 days ago
Why We Can't Retrofit Old Security Principles Onto AI Agents
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Why We Can't Retrofit Old Security Principles Onto AI Agents
🛡️
AI Security
arXiv
·
6d
6 days ago
Defending against Adaptive
Prompt
Injection
Attacks
via Reasoning-enabled Task Alignment
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment
🔓
Hacking
OffSec
·
6d
6 days ago
AI vs Traditional Penetration Testing: Tooling and Outcomes
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for AI vs Traditional Penetration Testing: Tooling and Outcomes
🇨🇳
Chinese AI
medium.com
·
3d
3 days ago
I Tested 5 AI Tools for Digital Real Estate: Here’s What Actually Made Money in 2026
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for I Tested 5 AI Tools for Digital Real Estate: Here’s What Actually Made Money in 2026
🪄
Prompt Engineering
HiddenLayer
·
5d
5 days ago
https://
www.hiddenlayer.com/research/updating-hiddenlayers-ape-taxonomy-a-new-objective-model-for-ai-attacks
Covered by
This Week In 4n6
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for https://www.hiddenlayer.com/research/updating-hiddenlayers-ape-taxonomy-a-new-objective-model-for-ai-attacks
🛡️
AI Security
medium.com
·
3d
3 days ago
# Fictional Framing as a
Prompt
Injection
Vector
: A Reproducibility Study on GPT-4o and Claude
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for # Fictional Framing as a Prompt Injection Vector: A Reproducibility Study on GPT-4o and Claude
« Page 1
·
Page 3 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous post
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
Discover
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
Like
Save
Not for me
Report