Prompt Injection

Feeds to Scour
SubscribedAll
Scoured 289 posts in 5.7 ms

Assessing Automated Prompt Injection Attacks in Agentic Environments

 ⚙️Prompt Engineering  Content type: Academic
arxiv.org·

Indirect Prompt Injection remains a fundamental security challenge for AI

 ⚙️Prompt Engineering  Content type: Blog
brave.com·

Your AI Agent Can Read. That’s the Whole Problem.

 ⚙️Prompt Engineering  Content type: Blog
medium.com·

Claude Code vulnerability exposes developer credentials via prompt injection

 ⚙️Prompt Engineering
4sysops.com·

Zero-Click IP Leak in a Privacy Search Engine: Indirect Prompt Injection & Silent Patching

 ⚙️Prompt Engineering
infosecwriteups.com
·

Security Flaw in Claude Code Illustrates the Risk of AI in Developer Workflows

 ⚙️Prompt Engineering
devops.com·

AI Pentesting Roadmap: Labs, Challenges, Writeups & Research

 ⚙️Prompt Engineering  Content type: Blog
osintteam.blog
·

Infosecurity Europe: Prompt Injection Remains Unsolved, OWASP Researcher Warns

 ⚙️Prompt Engineering  Content type: News
infosecurity-magazine.com·

Mathematical proof reveals why fixed AI guardrails can never block every jailbreak

 🤖AI Agents
techxplore.com·

RoboHack AI CTF (Robotic Hacking Community at DEFCON 34)

 ⚙️Prompt Engineering
ctftime.org·

ChatGPT can be hijacked without you knowing. Lockdown Mode is the fix

 ⚙️Prompt Engineering  Content type: News
pcworld.com·

Why OpenAI is disabling ChatGPT web access to fight prompt injection attacks

 ⚙️Prompt Engineering  Content type: News
livemint.com·

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

 🤖AI Agents  Content type: Academic
arxiv.org·

How to Defend Against Prompt Injection in Production

 ⚙️Prompt Engineering  Content type: Reference
leanpub.com··DEV

Beyond the OWASP Top 10: Securing GenAI Apps with Google Cloud Model Armor

 ⚙️Prompt Engineering  Content type: Blog
medium.com
·

How ChatGPT's new Lockdown mode protects you from data theft (and what else it does)

 ⚙️Prompt Engineering  Content type: News
zdnet.com·
Less-relevant results

Every set of AI guardrails can be broken by the right prompt

 ⚙️Prompt Engineering
helpnetsecurity.com·

Meet Hades: The malware that lies to AI security agents

 ✨Generative AI  Content type: News
infoworld.com··Hacker News

ChatGPT's new Lockdown Mode lets you disable web access and more to protect sensitive data from prompt injection

 ⚙️Prompt Engineering
the-decoder.com
·

Inside ChatGPT’s New Lockdown Mode: Is Your Data Safer?

 ⚙️Prompt Engineering
telecomtalk.info·

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