AI Security

Feeds to Scour
SubscribedAll
Scoured 62 posts in 13.6 ms

Sequential Data Poisoning in LLM Post-Training

 LLMs  Content type: Academic
arxiv.org·

Prompt Injection in RAG Agentic Systems

 🪄Prompt Engineering
ulad.net··Hacker News

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··Hacker News

Polymarket Annotation Injection

 🪄Prompt Engineering

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks

 🪄Prompt Engineering

Assessing Automated Prompt Injection Attacks in Agentic Environments

 💉Prompt Injection  Content type: Academic
arxiv.org·

Meet Hades: The malware that lies to AI security agents

 🪄Prompt Engineering  Content type: News

Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets

 🕹️Agentic AI  Content type: Blog
varonis.com··Hacker News

OpenAI Help: Lockdown Mode

 🪄Prompt Engineering
simonwillison.net·

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

 🔧Agent Tooling  Content type: Code
github.com··Hacker News

ChatGPT Introduces Lockdown Mode to Everyone, Preventing Prompt Injection Attacks

 🪄Prompt Engineering
researchsnipers.com·

The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection

 🪄Prompt Engineering  Content type: Academic
arxiv.org·

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

 🪄Prompt Engineering
thehackernews.com·

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

 🪄Prompt Engineering  Content type: Academic
arxiv.org·

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

OpenAI Rolls Out Lockdown Mode to Fight Prompt Injection Attacks

 🪄Prompt Engineering  Content type: News
pcmag.com·

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··Hacker News

GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines

 🪄Prompt Engineering  Content type: Academic
arxiv.org·

Casual experiment hint that models seem to search for different stuff

 🤖AI
spock.is··Hacker News

My side of the jqwik anti AI logging drama

 🕵️AI Agents  Content type: Blog

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