Artificial Intelligence

Prompt Injection Attack

Prompt Injection

Machine Learning

Llm Security

Explore recommended reads, summarized by AI

LLM Vulnerabilities and Defenses

Technical explorations of security weaknesses in large language models and methods to prevent them.

Exploiting LLM Systems and Agents

Prompt Injection and Output Security

Popular this week

In

InfoSec Write-ups

by

Nilo_ofar

Lakera’s Break The Agent Challenge— Solace AI Write-up

Sathishkumar Babu

Running Llama Prompt Guard 2 Locally: A Complete Guide to RAG Security

In

AI for Backend Engineers

by

Navya Devadiga

11 MCP Server Mistakes Behind This Autumn’s CVEs, Each Fixed in Python

In

AI for Backend Engineers

by

Navya Devadiga

Agent Memory Poisoning Is the Prompt Injection That Outlives the Session (OWASP ASI06)

MR SHAN

Exploiting AI agents to perform destructive actions

Latest stories

In

AI for Backend Engineers

by

Navya Devadiga

Agent Memory Poisoning Is the Prompt Injection That Outlives the Session (OWASP ASI06)

In

AI for Backend Engineers

by

Navya Devadiga

Indirect Prompt Injection Is a Data-Flow Bug: 10 Paths Into Your Agent’s Tools

In

AI for Backend Engineers

by

Navya Devadiga

11 MCP Server Mistakes Behind This Autumn’s CVEs, Each Fixed in Python

Eng Soon Cheah

NVIDIA Garak: the nmap of the LLM world

Erwin Hermanto

Prompt Injection Attacks: How We Secured Our LLM-Powered Chatbot

See more stories

Who to follow

Popular this week

In

InfoSec Write-ups

by

Nilo_ofar

Lakera’s Break The Agent Challenge— Solace AI Write-up

Sathishkumar Babu

Running Llama Prompt Guard 2 Locally: A Complete Guide to RAG Security

In

AI for Backend Engineers

by

Navya Devadiga

11 MCP Server Mistakes Behind This Autumn’s CVEs, Each Fixed in Python

In

AI for Backend Engineers

by

Navya Devadiga

Agent Memory Poisoning Is the Prompt Injection That Outlives the Session (OWASP ASI06)

MR SHAN

Exploiting AI agents to perform destructive actions

Latest stories

In

AI for Backend Engineers

by

Navya Devadiga

Agent Memory Poisoning Is the Prompt Injection That Outlives the Session (OWASP ASI06)

In

AI for Backend Engineers

by

Navya Devadiga

Indirect Prompt Injection Is a Data-Flow Bug: 10 Paths Into Your Agent’s Tools

In

AI for Backend Engineers

by

Navya Devadiga

11 MCP Server Mistakes Behind This Autumn’s CVEs, Each Fixed in Python

Eng Soon Cheah

NVIDIA Garak: the nmap of the LLM world

Erwin Hermanto

Prompt Injection Attacks: How We Secured Our LLM-Powered Chatbot

See more stories

Who to follow