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
Prompt Injection
💉 Prompt Injection
Specific
prompt injection attack, LLM security, jailbreak, AI vulnerability
Filter Results
Timeframe
Choose a timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
289
posts in
15.3
ms
🛡️
AI Security
4sysops
·
3d
3 days 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
Simon Willison’s Weblog
·
2d
2 days ago
Prompt
Injection
as Role Confusion
Covers
A Theory of Why Prompt Injection Works
Covered by
3 sources
See all sources covering this story
including
Schneier on Security
,
tldr.tech
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 as Role Confusion
🛡️
AI Security
arXiv
·
17h
17 hours ago
How Reliable Is Your
Jailbreak
Judge? Calibration and
Adversarial
Robustness of Automated ASR Scoring
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 How Reliable Is Your Jailbreak Judge? Calibration and Adversarial Robustness of Automated ASR Scoring
🛡️
AI Security
beSpacific
·
19h
19 hours ago
Prompt
Injection
: What Lawyers Considering Agentic
AI
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: What Lawyers Considering Agentic AI
🛡️
AI Security
medium.com
·
2d
2 days ago
Intent Doesn’t Lie. How TIKOS® Stopped Every
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 Intent Doesn’t Lie. How TIKOS® Stopped Every Prompt Injection
🕳
LLM Vulnerabilities
latent.space
·
3d
3 days 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
tldr.tech
,
contextmaestro.com
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 after Mythos — Zico Kolter & Matt Fredrikson, Gray Swan
💬
LLM Prompting
GitHub
·
1d
1 day ago
The proxy that stops your colleague from
leaking
another database
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 The proxy that stops your colleague from leaking another database
🛡️
AI Security
easternherald.com
·
3d
3 days 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
Infosecurity Magazine
·
1d
1 day ago
macOS Backdoor Uses
Prompt
Injection
to Evade
AI
Triage
Covers
macOS.Gaslight | Rust Backdoor Turns Prompt Injection on the Analyst, Not the Sandbox
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 macOS Backdoor Uses Prompt Injection to Evade AI Triage
💬
LLM Prompting
indiehacker.news
·
1d
1 day ago
#084 - Google fired the dev who built their 28K-star CLI,
LLM
caching hides a 120x pricing gap
Covers
11 stories
See all stories this covers
including
Try API on DeepSeek, It's really super fast and cheap
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 #084 - Google fired the dev who built their 28K-star CLI, LLM caching hides a 120x pricing gap
🕳
LLM Vulnerabilities
paddo.dev
·
5d
5 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.
🤖
Agentic Engineering
Palo Alto Networks Blog
·
6d
6 days ago
Expanding Our Footprint: Local Cloud Availability for Prisma AIRS in Japan
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 Expanding Our Footprint: Local Cloud Availability for Prisma AIRS in Japan
✍️
Prompt Engineering
ryandens.github.io
·
3d
3 days 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
✍️
Prompt Engineering
medium.com
·
5d
5 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?
✍️
Prompt Engineering
medium.com
·
6d
6 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
🕳
LLM Vulnerabilities
arXiv
·
17h
17 hours ago
A Red Teaming Framework for Large Language
Models
: A Case Study on Faithfulness Evaluation
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 Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation
🕳
LLM Vulnerabilities
arXiv
·
17h
17 hours ago
What Intermediate Layers Know: Detecting
Jailbreaks
from Entropy Dynamics
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 What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics
🧠
LLM
arXiv
·
17h
17 hours ago
RAS: Measuring
LLM
Safety Through Refusal
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 RAS: Measuring LLM Safety Through Refusal Alignment
🧠
Claude
arXiv
·
2d
2 days 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
🕳
LLM Vulnerabilities
arXiv
·
1d
1 day ago
PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image
Jailbreak
Evaluation
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 PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation
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