Promptinjection

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Leo

Jul 23

Pillar research says the AI coding agent sandbox leaks through trusted files

#aiagents #sandbox #promptinjection #security

2 min read

Edison Flores

Jul 23

L1.9: I built a prompt injection firewall for AI agents (28 detection rules)

#ai #security #mcp #promptinjection

2 min read

Leo

Jul 18

OpenAI ships GPT-Red to automate prompt-injection testing against AI agents

#aiagents #promptinjection #security #testing

2 min read

Basavaraj SH

Jul 16

Prompt Injection: The AI Security Hole Every Builder Should Know

#ai #security #promptinjection #machinelearning

2 min read

Diego Diaz

Jul 14

The MCP Confused Deputy: Provenance Gaps, Instruction Injection, and DNS Rebinding in the Model Context Protocol

#mcp #confuseddeputy #promptinjection #dnsrebinding

7 min read

Pykero

Jul 15

AI Agent Security: A Pre-Launch Checklist for Founders

#aisecurity #aiagents #llmsecurity #promptinjection

4 min read

Michael "Mike" K. Saleme

Jul 9

An AI agent leaked private repos without ever breaking a single permission

#aiagents #security #llm #promptinjection

3 min read

Breach Protocol

Jul 1

A security writeup catalogs how AI agents get attacked -- and one claim raised eyebrows

#security #agents #promptinjection #aisafety

2 min read

eyanpen

Jun 28

Does Your AI Agent Need Prompt Protection? A Practical Decision Guide

#promptinjection #aiagentsecurity #threatmodel #leastprivilege

5 min read

PolicyLayer

Jun 16

Tool-Result Injection: The MCP Attack System Prompts Miss

#mcp #security #promptinjection #architecture

7 min read

PolicyLayer

Jun 16

System Prompts vs. Transport Firewalls: Why System Prompts Do Not Equal Security

#security #mcp #promptinjection #architecture

3 min read

PolicyLayer

Jun 16

Blocking Outbound Exfiltration Through MCP Fetch and HTTP Tools

#mcp #security #policy #promptinjection

4 min read

Ecaterina Sevciuc

Jul 15

AURA (AI User Risk Assessment): A behavioral threat-intelligence framework for AI Safety

#aisafety #promptinjection #llmsecurity #redteaming

2 min read

Arthur

Jul 3

The System Prompt Is Not a Security Boundary

#aiagents #llm #security #promptinjection

8 min read

Toni Antunovic

Jun 9

The Gemini CLI CVSS 10 Attack: How a GitHub Issue Became a Supply Chain Weapon

#security #promptinjection #supplychainsecurity #devsecops

6 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.