AI Security

Feeds to Scour
SubscribedAll
Scoured 85 posts in 8.2 ms

Config Files That Run Code: Supply Chain Security Blindspot

 🛡️Guardrails
safedep.io··Hacker News

What a Regex Can't Do: A Bayesian Governor for OpenClaw's Tool Calls

 🛡️Guardrails  Content type: Blog
gfrm.in··Hacker News

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation

 🛡️Guardrails  Content type: Academic
arxiv.org·

Actenon/actenon-kernel: Stop AI agents from taking destructive actions they weren't authorized to. Actenon gates consequential actions, payments, deletes, deploys, access changes, so nothing executes without a cryptographic proof bound to that exact action. Every decision leaves a verifiable receipt. Open-source, runs locally. No valid proof, no execution.

 🤖AI Agents  Content type: Code
github.com··DEV

AI Email Agents Are Phishable: How OpenClaw Spilled User Data to Social Engineering Attacks

 ✍️Prompt Engineering  Content type: Blog
dev.to··DEV

Securing the Retrieval-Augmented Generation (RAG)

 🔍RAG  Content type: Blog
dev.to··DEV

Show HN: Jo – AI-native language to catch prompt injection at compile-time

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

Rails GuardDog: Advanced Security Scanner for Rails Applications

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

Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection

 🛡️Guardrails  Content type: Academic
arxiv.org·

sausin/outpost: Removing AI agents' quiet security problem

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

SkillSpector — Vendor-Backed Security Scanner for AI Agent Skills, Well-Scoped but Dependent on Static Patterns

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

The complete guide to claude code permissions list

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

I built the tool StackOne's CEO said every developer needs

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

VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation

 🛡️Guardrails  Content type: Academic
arxiv.org·

Web MCP: give some tools to your agent

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

The Paradox of Vibe Coding - In the Age of LLM-Written Code, Who Protects the LLM?

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

I Built an Adversarial Eval Framework and Attacked 5 LLMs — Every Single One Failed

 🌐Open Source AI  Content type: Blog
dev.to··DEV

Anyone with GitHub issue access can steal your CI/CD secrets. Here's why.

 ✍️Prompt Engineering  Content type: Blog
dev.to··DEV

I benchmarked Python AI-app security scanners. Here's what each catches.

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

Zerobox: The Sandbox Layer Your AI Agent's Exec Tool Has Always Needed

 🔍RAG  Content type: Blog
dev.to··DEV

No more posts from alanxu.80's subscribed feeds.

Sign up or log in to see more results

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