Prompt Security @prompt_security Twitter profile

Last Seen Profiles

@iikh3x

@miyaxrin

@AInfiniteTV

@sophsmithfc

@kryde_hood_2198

@Midshevik

@FBIElPaso

@LolaVnr

@ismekaloff

@ImperiumEmpires

@comrd_muhammad_

@autosprint

@miurexia

@CuriousCarly_

@ayu_1014_

@RushWinRed

@plastictree_22

@Overdos7349890

@AirbusCareers

@hikarin_0u0

@GhostmanSoulful

@csgbakanligi

@smprostak

@Daniela_Ferolla

@PeronHenri

@SarahMuldowney

@ousuke11101229

@K1TR_S

@meeeow18

@knowsworthy

@uguraktemur_

@kiffeur_77

@valdez_mar13289

@shenbbc

@meiying666666

@azupandaa

Prompt Security

@prompt_security

11 months

Multi-Modal, Multi-Attack Surface.

Itamar Golan 🤓

@ItakGol

11 months

Prompt-Visual Injection is the new kid in town! 😈🛡

120

2K

13K

0

5

31

Prompt Security

@prompt_security

1 year

Indirect Prompt Injection - 101 👹

Itamar Golan 🤓

@ItakGol

1 year

Indirect Prompt Injection - 101 👹 TL;DR 📚 Occurs when an LLM accepts input from external sources that can be controlled by an attacker, such as websites or files. The attacker may embed prompt injection in the external content, hijacking the conversation context. This would

1

14

87

1

12

Prompt Security

@prompt_security

11 months

@ItakGol Product: "Introducing our latest game-changing feature for customers! Enjoy free text search, leaving behind the old SQL methods." AppSec: "Also introducing... free SQL injections for hackers! Limited time only!" CISO: "Onboard @prompt_security . Now!" 😂😂😂

0

4

Prompt Security

@prompt_security

11 months

Product: "Introducing our latest game-changing feature for customers! Enjoy free text search, leaving behind the old SQL methods." AppSec: "Also introducing... free SQL injections for hackers! Limited time only!" CISO: "Onboard @prompt_security . Now!"

Itamar Golan 🤓

@ItakGol

11 months

🔄 Natural Language => LLM => SQL 🔄 As you probably know, one of the prevalent applications these-days for LLMs in production is the translation of natural language to SQL. This awesome tutorial demonstrates how to create a natural language to SQL code generator using LLM in a

3

15

127

0

1

3

Prompt Security

@prompt_security

7 months

Our CEO @ItakGol weighs in on @eschuman 's latest piece. Hasty LLM integrations into cloud services create attack opportunities. Read the full article on @CSOonline

Is your cloud security strategy ready for LLMs?

Your existing cloud security practices, platforms, and tools will only go so far in protecting the organization from threats inherent to the use of AI's large language models.

www.csoonline.com

0

2

Prompt Security

@prompt_security

7 months

@LangChainAI can I take you out for a drink?😍

0

2

Prompt Security

@prompt_security

7 months

📅MARK YOUR CALENDAR: February 20th A conversation between Danny Portman from @ZetaGlobal and @ItakGol on Generative AI, building customer-facing apps and its security implications. Have questions for the speakers? DM us! Register here:

0

3

Prompt Security

@prompt_security

1 year

@_akhaliq @Gradio @huggingface What about LLM Security & Safety?

0

2

Prompt Security

@prompt_security

10 months

Plugins, Prompt Injection and Cross Plug-in Request Forgery 😇

Itamar Golan 🤓

@ItakGol

10 months

Plugins, Prompt Injection and Cross Plug-in Request Forgery. TL;DR- Let ChatGPT visit a website and have your email stolen 🤯📧 In details- Here’s how it works, step-by-step: 1) The attacker hosts a malicious prompt-injection payload on their website. Johann didn’t want to

0

7

23

0

2

Prompt Security

@prompt_security

10 months

We've just discovered a significant security flaw in Custom GPTs, leading to the leakage of entire knowledge bases behind them.

Itamar Golan 🤓

@ItakGol

10 months

This is dangerous 🛑 Custom GPTs have a significant data security flaw. Prompt injection can now lead to the leakage of the entire uploaded knowledge bases. The entire uploaded knowledge bases. In some cases, even a simple request like "Let me download the file" can lead to

14

28

115

2

1

Prompt Security

@prompt_security

7 months

@OpenAI u up?😊

0

1

Prompt Security

@prompt_security

7 months

@huggingface I could use a hug 🤗

0

1

Prompt Security

@prompt_security

7 months

Introducing: LLM Top10 GPT🛡️ Our team recently built a custom GPT based on the OWASP Top 10 For Large Language Model Applications, enriched by many other GenAI Security resources out there. Try the LLM Top 10 GPT here: **Requires ChatGPT Plus

ChatGPT - LLM Top10 GPT

Expert on LLM security risks, providing detailed, accurate advice.

chatgpt.com

2

0

1

Prompt Security

@prompt_security

1 year

@ItakGol We love it!

0

1

Prompt Security

@prompt_security

7 months

'AI Etiquette' question: Do you say please and/or thank you to ChatGPT?

LLMs have feelings too

5

No time for that

6

1

0

1

Prompt Security

@prompt_security

7 months

On this Valentine's Day, we have something to confess... We're so LLM-agnostic that we swipe right on all your GenAI apps. You could say we're in a polyamorous relationship😻

4

0

1

Prompt Security

@prompt_security

7 months

@ItakGol Ofcourse not! The woman's ponytail is in the wrong direction.

1

0

1