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
Specific
prompt injection, jailbreak, AI safety, red teaming, threat model
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
87
posts in
9.2
ms
Breaking LiteLLM: From Low-Privilege User to Admin and RCE (CVE-2026-47101, CVE-2026-47102, CVE-2026-40217)
🌐
Open Source AI
Content type:
Blog
obsidiansecurity.com
·
10h
10 hours ago
·
Hacker News
Actions for Breaking LiteLLM: From Low-Privilege User to Admin and RCE (CVE-2026-47101, CVE-2026-47102, CVE-2026-40217)
My side of the jqwik anti
AI
logging drama
🛡️
Guardrails
Content type:
Blog
blog.johanneslink.net
·
3d
3 days ago
·
Lobsters
,
Hacker News
,
Hacker News
Actions for My side of the jqwik anti AI logging drama
Microsoft Agent 365 Resources
🎼
Agent Orchestration
microsoft.github.io
·
1d
1 day ago
·
Hacker News
Actions for Microsoft Agent 365 Resources
inflightsec/agent-vault-proxy: Just-in-time API keys for
AI
agents - and any other process you route through it: the caller only ever sees a placeholder.
🛡️
Guardrails
Content type:
Code
github.com
·
15h
15 hours ago
·
Hacker News
Actions for inflightsec/agent-vault-proxy: Just-in-time API keys for AI agents - and any other process you route through it: the caller only ever sees a placeholder.
Is
security
a skill issue? Five scanners, 3,084 skills, a different verdict 64% of the time
🛡️
Guardrails
trymastro.com
·
1d
1 day ago
·
Hacker News
Actions for Is security a skill issue? Five scanners, 3,084 skills, a different verdict 64% of the time
AI
Prompt
Security
: Is the Same Protection Necessary for Every
🛡️
Guardrails
Content type:
Blog
dev.to
·
2d
2 days ago
·
DEV
Actions for AI Prompt Security: Is the Same Protection Necessary for Every
If You Use Claude or Gemini, This Microsoft Breach Means Your Data Is at Risk
🛡️
Guardrails
scienspire.com
·
4d
4 days ago
·
Hacker News
Actions for If You Use Claude or Gemini, This Microsoft Breach Means Your Data Is at Risk
Brain-Prompt
Injection
: A
Route-Safety
Audit for BCI-LLM Agents
🛡️
Guardrails
Content type:
Academic
arxiv.org
·
3d
3 days ago
Actions for Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents
DreamHost is shutting down Mailman – decision made sense, the execution didn't
🛡️
Guardrails
Content type:
Blog
emparrot.com
·
2d
2 days ago
·
Hacker News
Actions for DreamHost is shutting down Mailman – decision made sense, the execution didn't
The complete guide to
llm
and genai data
security
best practices
🛡️
Guardrails
Content type:
Blog
dev.to
·
1d
1 day ago
·
DEV
Actions for The complete guide to llm and genai data security best practices
Meet Hades: The malware that lies to
AI
security
agents
🧠
LLMs
Content type:
News
infoworld.com
·
3d
3 days ago
·
Hacker News
Actions for Meet Hades: The malware that lies to AI security agents
agentsploit/agentsploit: Offensive
security
framework for
AI
agents and MCP servers.
🛡️
Guardrails
Content type:
Code
github.com
·
2d
2 days ago
·
Hacker News
Actions for agentsploit/agentsploit: Offensive security framework for AI agents and MCP servers.
PRISM: Recovering Instruction Sets from Language
Model
Activations
🛡️
Guardrails
Content type:
Academic
arxiv.org
·
3d
3 days ago
Actions for PRISM: Recovering Instruction Sets from Language Model Activations
E.L.L.A. — Embedded Local Logic Agent
🛡️
Guardrails
Content type:
Blog
dev.to
·
2d
2 days ago
·
DEV
Actions for E.L.L.A. — Embedded Local Logic Agent
Community Web UI (unofficial)
💾
Agent Memory
get-hermes.ai
·
5d
5 days ago
·
Hacker News
Actions for Community Web UI (unofficial)
Co-authored-by is a Lie: Cryptographic Provenance for
AI
Coding Agents | Ryan Duffy - Building with
AI
🛡️
Guardrails
Content type:
Blog
blog.rduffy.uk
·
6d
6 days ago
·
Hacker News
Actions for Co-authored-by is a Lie: Cryptographic Provenance for AI Coding Agents | Ryan Duffy - Building with AI
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 Frameworks
Content type:
Code
github.com
·
2d
2 days ago
·
Hacker News
,
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.
Mini Shai-Hulud, Miasma, and Hades Worms Target Bioinformatics and MCP Developers via Malicious PyPI Wheels
🧩
AI Frameworks
Content type:
Blog
socket.dev
·
3d
3 days ago
·
Hacker News
Actions for Mini Shai-Hulud, Miasma, and Hades Worms Target Bioinformatics and MCP Developers via Malicious PyPI Wheels
I Scanned 492 MCP Servers Exposed to the Internet. Here's What I Found.
🛡️
Guardrails
Content type:
Blog
dev.to
·
20h
20 hours ago
·
DEV
Actions for I Scanned 492 MCP Servers Exposed to the Internet. Here's What I Found.
Learning
to Attack and Defend: Adaptive
Red
Teaming
of Language Models via GRPO
⚙️
MLOps
Content type:
Academic
arxiv.org
·
3d
3 days ago
Actions for Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO
« Page 1
·
Page 3 »
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