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
AI Security
🛡️ AI Security
Model Poisoning, Adversarial Examples, Prompt Injection, AI Safety
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
62
posts in
13.6
ms
Sequential
Data
Poisoning
in
LLM
Post-Training
✨
LLMs
Content type:
Academic
arxiv.org
·
6d
6 days ago
Actions for Sequential Data Poisoning in LLM Post-Training
Prompt
Injection
in RAG Agentic Systems
🪄
Prompt Engineering
ulad.net
·
2d
2 days ago
·
Hacker News
Actions for Prompt Injection in RAG Agentic Systems
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.
👨💻
AI Coding
Content type:
Code
github.com
·
19h
19 hours 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.
Polymarket Annotation
Injection
🪄
Prompt Engineering
sam.elborai.me
·
2d
2 days ago
·
Hacker News
Actions for Polymarket Annotation Injection
OpenAI unveils Lockdown
Mode
to protect sensitive
data
from
prompt
injection attacks
🪄
Prompt Engineering
techcrunch.com
·
3d
3 days ago
·
Hacker News
Actions for OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
Assessing Automated
Prompt
Injection
Attacks
in Agentic Environments
💉
Prompt Injection
Content type:
Academic
arxiv.org
·
8h
8 hours ago
Actions for Assessing Automated Prompt Injection Attacks in Agentic Environments
Meet Hades: The malware that lies to
AI
security
agents
🪄
Prompt Engineering
Content type:
News
infoworld.com
·
1d
1 day ago
·
Hacker News
Actions for Meet Hades: The malware that lies to AI security agents
Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets
🕹️
Agentic AI
Content type:
Blog
varonis.com
·
23h
23 hours ago
·
Hacker News
Actions for Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets
OpenAI Help: Lockdown
Mode
🪄
Prompt Engineering
simonwillison.net
·
4d
4 days ago
Actions for OpenAI Help: Lockdown Mode
agentsploit/agentsploit: Offensive
security
framework for
AI
agents and MCP servers.
🔧
Agent Tooling
Content type:
Code
github.com
·
23h
23 hours ago
·
Hacker News
Actions for agentsploit/agentsploit: Offensive security framework for AI agents and MCP servers.
ChatGPT Introduces Lockdown
Mode
to Everyone, Preventing
Prompt
Injection
Attacks
🪄
Prompt Engineering
researchsnipers.com
·
4d
4 days ago
Actions for ChatGPT Introduces Lockdown Mode to Everyone, Preventing Prompt Injection Attacks
The
Injection
Paradox: Brand-Level Suppression in
Safety-Trained
LLM
Recommendations via RAG Context
Injection
🪄
Prompt Engineering
Content type:
Academic
arxiv.org
·
1d
1 day ago
Actions for The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection
New ChatGPT Lockdown
Mode
Limits Tools That Could Enable
Data
Exfiltration
🪄
Prompt Engineering
thehackernews.com
·
3d
3 days ago
Actions for New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration
Toward
Secure
LLM
Agents: Threat Surfaces,
Attacks
, Defenses, and Evaluation
🪄
Prompt Engineering
Content type:
Academic
arxiv.org
·
8h
8 hours ago
Actions for Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
Miasma Worm Hits Microsoft Again: Azure Functions Action and 72 Other Repositories Disabled After Supply Chain
Attack
Targeting
AI
Coding Agents
🔌
Claude Plugins
Content type:
Blog
stepsecurity.io
·
1d
1 day ago
·
Hacker News
Actions for Miasma Worm Hits Microsoft Again: Azure Functions Action and 72 Other Repositories Disabled After Supply Chain Attack Targeting AI Coding Agents
OpenAI Rolls Out Lockdown
Mode
to Fight
Prompt
Injection
Attacks
🪄
Prompt Engineering
Content type:
News
pcmag.com
·
3d
3 days ago
Actions for OpenAI Rolls Out Lockdown Mode to Fight Prompt Injection Attacks
CODEANDTRUST/clawcall: Give your OpenClaw / self-hosted
AI
agent inbound phone calls - a Twilio-to-gateway voice bridge with working agent tools mid-call (MIT).
🖥️
Homelab
Content type:
Code
github.com
·
1d
1 day ago
·
Hacker News
Actions for CODEANDTRUST/clawcall: Give your OpenClaw / self-hosted AI agent inbound phone calls - a Twilio-to-gateway voice bridge with working agent tools mid-call (MIT).
GitInject: Real-World
Prompt
Injection
Attacks
in AI-Powered CI/CD Pipelines
🪄
Prompt Engineering
Content type:
Academic
arxiv.org
·
8h
8 hours ago
Actions for GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines
Casual experiment hint that
models
seem to search for different stuff
🤖
AI
spock.is
·
5d
5 days ago
·
Hacker News
Actions for Casual experiment hint that models seem to search for different stuff
My side of the jqwik anti
AI
logging drama
🕵️
AI Agents
Content type:
Blog
blog.johanneslink.net
·
1d
1 day ago
·
Hacker News
Actions for My side of the jqwik anti AI logging drama
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