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 Vulnerabilities
🕳 LLM Vulnerabilities
Specific
Hacking LLMs, Prompt Injection
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
228
posts in
24.6
ms
Assessing Automated
Prompt
Injection
Attacks
in Agentic Environments
💉
Prompt Injection
Content type:
Academic
arxiv.org
·
14h
14 hours ago
Actions for Assessing Automated Prompt Injection Attacks in Agentic Environments
Indirect
Prompt
Injection
remains a fundamental security challenge for AI
💉
Prompt Injection
Content type:
Blog
brave.com
·
2d
2 days ago
Actions for Indirect Prompt Injection remains a fundamental security challenge for AI
ChatGPT Introduces Lockdown
Mode
to Everyone, Preventing
Prompt
Injection
Attacks
🛡️
AI Security
researchsnipers.com
·
4d
4 days ago
Actions for ChatGPT Introduces Lockdown Mode to Everyone, Preventing Prompt Injection Attacks
Mathematical proof reveals why fixed AI guardrails can never block every
jailbreak
💉
Prompt Injection
techxplore.com
·
2h
2 hours ago
Actions for Mathematical proof reveals why fixed AI guardrails can never block every jailbreak
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.
🤝
Multi-Agent Orchestration
Content type:
Code
github.com
·
1d
1 day ago
·
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.
Measuring Embedding Drift: Why Hybrid Search Saves Stale
Models
.
🔗
Hybrid Search
pub.towardsai.net
·
13h
13 hours ago
Actions for Measuring Embedding Drift: Why Hybrid Search Saves Stale Models.
Tiberius: A Security Testing Framework for
LLM
Applications in Java
💉
Prompt Injection
foojay.io
·
5d
5 days ago
Actions for Tiberius: A Security Testing Framework for LLM Applications in Java
Prompt
Injection
in RAG Agentic
Systems
💉
Prompt Injection
ulad.net
·
2d
2 days ago
·
Hacker News
Actions for Prompt Injection in RAG Agentic Systems
iOS 27
system
prompts
🔧
Developer tools
gist.github.com
·
1d
1 day ago
·
Lobsters
Actions for iOS 27 system prompts
From
prompt
to pwned: chaining
LLM
and web bugs to Admin
🛡️
AI Security
Content type:
Blog
blog.quarkslab.com
·
5d
5 days ago
Actions for From prompt to pwned: chaining LLM and web bugs to Admin
Humans and
LLMs
share a mental disorder: Fugue Lock
🦉
Qwen
vwwwv.org
·
1d
1 day ago
·
Hacker News
Actions for Humans and LLMs share a mental disorder: Fugue Lock
OpenAI unveils Lockdown
Mode
to protect sensitive data from
prompt
injection
attacks
💉
Prompt Injection
techcrunch.com
·
3d
3 days ago
·
Hacker News
Actions for OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
LLM
Observability: What To Instrument and How To Act on It
🪄
Prompt Engineering
Content type:
Blog
blog.n8n.io
·
2d
2 days ago
Actions for LLM Observability: What To Instrument and How To Act on It
vishal-dehurdle/state-harness: Runtime safety net for
LLM
agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip install state-harness
🎭
Claude
Content type:
Code
github.com
·
23h
23 hours ago
·
Hacker News
Actions for vishal-dehurdle/state-harness: Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip install state-harness
Toward Secure
LLM
Agents: Threat Surfaces,
Attacks
, Defenses, and Evaluation
💉
Prompt Injection
Content type:
Academic
arxiv.org
·
14h
14 hours ago
Actions for Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
OpenAI Help: Lockdown
Mode
💉
Prompt Injection
simonwillison.net
·
4d
4 days ago
Actions for OpenAI Help: Lockdown Mode
Comparing Claude Fable 5's
system
prompt
to Opus 4.8
💻
Claude Code
Content type:
Blog
twelvetables.blog
·
1d
1 day ago
·
Hacker News
Actions for Comparing Claude Fable 5's system prompt to Opus 4.8
ChatGPT easily bypasses its own guardrails; all
LLMs
are inherently unsafe
🎭
Claude
Content type:
Blog
techzine.eu
·
4d
4 days ago
Actions for ChatGPT easily bypasses its own guardrails; all LLMs are inherently unsafe
Less-relevant results
Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 (@elder_plinius)
🎭
Claude
xcancel.com
·
5h
5 hours ago
·
Hacker News
Actions for Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 (@elder_plinius)
Purpose-built local AI agents
🤖
AI
Content type:
Blog
samihonkonen.com
·
1d
1 day ago
·
Hacker News
Actions for Purpose-built local AI agents
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