Prompt Engineering

Feeds to Scour
SubscribedAll
Scoured 151 posts in 15.3 ms

What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in Agentic Systems

 🛡️AI Security  Content type: Academic
arxiv.org·

Prompt Injection in RAG Agentic Systems

 🔧Agent Tooling
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

Tokenminning: Because Tokenmaxxing Is a Bad Idea

 🤖LLM
tokenminning.com··Hacker News

Polymarket Annotation Injection

 🛡️AI Security
sam.elborai.me··Hacker News

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

 🛡️AI Security
techcrunch.com··Hacker News

Assessing Automated Prompt Injection Attacks in Agentic Environments

 💉Prompt Injection  Content type: Academic
arxiv.org·

Melanie Mitchell: What We Get Wrong About AI

 🤖LLM
yalereview.org··Substack, Hacker News, Hacker News

OpenAI Help: Lockdown Mode

 🛡️AI Security
simonwillison.net·

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

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

Meet Hades: The malware that lies to AI security agents

 📦Software Supply Chain  Content type: News
infoworld.com··Hacker News

ChatGPT Introduces Lockdown Mode to Everyone, Preventing Prompt Injection Attacks

 🛡️AI Security
researchsnipers.com·

A free diagnostic for the Claude Certified Architect exam

 🔌Claude Plugins  Content type: Discussion  Content type: Tutorial
claudecertifiedarchitects.com··Hacker News

Evaluating Advanced Prompting on Gemini Flash for Multi-Hop Biomedical QA

 ✨Gemini  Content type: Academic
arxiv.org·

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

 🛡️AI Security
thehackernews.com·

Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets

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

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

Dep-LLM: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable LLM Reasoning

 🤖LLM  Content type: Academic
arxiv.org·

StereoTales: Multilingual Open-Ended Stereotype Discovery in LLMs

 💬NLP  Content type: Blog
research.giskard.ai··Hacker News

A wild idea: Abstract reality using ontology

 🤖LLM  Content type: Discussion
news.ycombinator.com··Hacker News

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