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
36.1
ms
💉
Prompt Injection
arXiv
·
5d
5 days ago
Understanding and Mitigating
Prompt
Leaking
Attacks
in Real-World LLM-Based Applications
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 Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications
🗜️
Vector Compression
Sami Honkonen
·
22h
22 hours ago
Guidance
injection
: reliable instructions for local
LLMs
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 Guidance injection: reliable instructions for local LLMs
💉
Prompt Injection
medium.com
·
2d
2 days ago
Fictional Framing Part 3: Does the Fix Generalize, or Did I Just Patch One Sentence?
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 Part 3: Does the Fix Generalize, or Did I Just Patch One Sentence?
🛡️
AI Security
role-confusion.github.io
·
16h
16 hours ago
A Theory of Why
Prompt
Injection
Works
Covers
2 stories
See all stories this covers
including
Playwright MCP Server – Snapshot based – faster and more reliable than images
Covered by
3 sources
See all sources covering this story
including
Simon Willison’s Weblog
,
LessWrong
Discussed on
Hacker News
and
Lobsters
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 A Theory of Why Prompt Injection Works
🎭
Claude
Claude Cookbook
·
48m
48 minutes ago
System
Prompts
– Claude API Docs
Covered by
Databricks
,
Tech Policy Press
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 System Prompts – Claude API Docs
⚖️
Dual-Use Technology
paddo.dev
·
2d
2 days ago
It Was Never the
Jailbreak
. It Was the Guest List.
Covers
The Korean Telecom Giant at the Center of Anthropic’s Mythos Controversy
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 It Was Never the Jailbreak. It Was the Guest List.
💉
Prompt Injection
Orca Security
·
5d
5 days ago
The Complete Guide to
LLM
Security: Risks, Best Practices, and Solutions
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 Complete Guide to LLM Security: Risks, Best Practices, and Solutions
🛡️
Content Moderation
latent.space
·
11h
11 hours ago
Red-Teaming
after Mythos — Zico Kolter & Matt Fredrikson, Gray Swan
Covers
The lethal trifecta for AI agents: private data, untrusted content, and external communication
Covered by
contextmaestro.com
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 Red-Teaming after Mythos — Zico Kolter & Matt Fredrikson, Gray Swan
💰
Tokenomics
tokoscope.com
·
1d
1 day ago
Automatic
LLM
token compression and cost monitoring in 2 lines
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 Automatic LLM token compression and cost monitoring in 2 lines
💉
Prompt Injection
4sysops
·
22h
22 hours ago
Malicious npm and PyPI packages use
prompt
injection
to bypass AI security scanners
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 Malicious npm and PyPI packages use prompt injection to bypass AI security scanners
🛡️
AI Security
GitHub
·
4d
4 days ago
AICU –
LLM
Red
Team
Vulnerability Scanner
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 AICU – LLM Red Team Vulnerability Scanner
🛡️
AI Security
easternherald.com
·
16h
16 hours ago
OrcaRouter Releases AI Threat Report 2026 and Makes Its Security Controls Free Amid Rise in
Prompt-Injection
Attacks
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 OrcaRouter Releases AI Threat Report 2026 and Makes Its Security Controls Free Amid Rise in Prompt-Injection Attacks
🛡️
AI Security
ryandens.github.io
·
1d
1 day ago
Promptblock
– detect prompt
injections
in GitHub issues
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 Promptblock – detect prompt injections in GitHub issues
🔎
AI Auditing
medium.com
·
2d
2 days ago
AI
Red
Teaming
: The Key to Testing Real-World
LLM
Risks and Vulnerabilities
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: The Key to Testing Real-World LLM Risks and Vulnerabilities
⚖️
Dual-Use Technology
risky.biz
·
6d
6 days ago
The state of the art in AI
model
jailbreaks
Covered by
lawfaremedia.org
,
news.risky.biz
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 state of the art in AI model jailbreaks
🎭
Claude
arXiv
·
4h
4 hours ago
BELLS-O: Evaluating the Operational Trade-offs of
LLM
Supervision
Systems
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 BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems
💉
Prompt Injection
OSINT Team Blog
·
5d
5 days ago
Anatomy of a Multi-Layer
Jailbreak
: Why This Payload Fires
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 Anatomy of a Multi-Layer Jailbreak: Why This Payload Fires
💉
Prompt Injection
GitHub
·
5d
5 days ago
A real
prompt-injection
case — and the blind spot it exposed in my own scanner
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 A real prompt-injection case — and the blind spot it exposed in my own scanner
💉
Prompt Injection
strandsagents.com
·
5d
5 days ago
Red-teaming
agents with the GOAT
attack
strategy
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 Red-teaming agents with the GOAT attack strategy
🛡️
AI Security
Socket
·
6d
6 days ago
npm Package Uses
Prompt
Injection
and Token Flooding to Disrupt AI Malware Scanners
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 npm Package Uses Prompt Injection and Token Flooding to Disrupt AI Malware Scanners
Page 2 »
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