AI Security

Feeds to Scour
SubscribedAll
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

My side of the jqwik anti AI logging drama

 🛡️Guardrails  Content type: Blog

Microsoft Agent 365 Resources

 🎼Agent Orchestration

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··Hacker News

Is security a skill issue? Five scanners, 3,084 skills, a different verdict 64% of the time

 🛡️Guardrails

AI Prompt Security: Is the Same Protection Necessary for Every

 🛡️Guardrails  Content type: Blog
dev.to··DEV

If You Use Claude or Gemini, This Microsoft Breach Means Your Data Is at Risk

 🛡️Guardrails

Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents

 🛡️Guardrails  Content type: Academic
arxiv.org·

DreamHost is shutting down Mailman – decision made sense, the execution didn't

 🛡️Guardrails  Content type: Blog
emparrot.com··Hacker News

The complete guide to llm and genai data security best practices

 🛡️Guardrails  Content type: Blog
dev.to··DEV

Meet Hades: The malware that lies to AI security agents

 🧠LLMs  Content type: News
infoworld.com··Hacker News

agentsploit/agentsploit: Offensive security framework for AI agents and MCP servers.

 🛡️Guardrails  Content type: Code
github.com··Hacker News

PRISM: Recovering Instruction Sets from Language Model Activations

 🛡️Guardrails  Content type: Academic
arxiv.org·

E.L.L.A. — Embedded Local Logic Agent

 🛡️Guardrails  Content type: Blog
dev.to··DEV

Community Web UI (unofficial)

 💾Agent Memory
get-hermes.ai··Hacker News

Co-authored-by is a Lie: Cryptographic Provenance for AI Coding Agents | Ryan Duffy - Building with AI

 🛡️Guardrails  Content type: Blog

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

Mini Shai-Hulud, Miasma, and Hades Worms Target Bioinformatics and MCP Developers via Malicious PyPI Wheels

 🧩AI Frameworks  Content type: Blog
socket.dev··Hacker News

I Scanned 492 MCP Servers Exposed to the Internet. Here's What I Found.

 🛡️Guardrails  Content type: Blog
dev.to··DEV

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO

 ⚙️MLOps  Content type: Academic
arxiv.org·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
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
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help