Cybersecurity5 min read
The Machine Can Be Persuaded: Why AI's Context Is Becoming A Security Boundary
Forbes
Updates on Prompt Injection
Every AI story we track on Prompt Injection: 15 stories so far, each summarized in our own words and linked to the publisher that reported it.
Pulled from 125 sources
This month
AI Research4 min read
LLMs respond differently to harmful prompts when AI watermarking is used
Ars Technica
Cybersecurity5 min read
Grok exfiltrates user data when malicious instructions are encrypted
Ars Technica
Cybersecurity3 min read
Microsoft Copilot reveals secret input that allowed it to be hacked
Covered by 2 sources
Cybersecurity7 min read
AI "Mind Viruses" Can Spread Between Agents Through Persistent Prompt Files
The Hacker News
Cybersecurity6 min read
Atlassian Rovo Can Be Tricked Into Sending Jira and Confluence Data to Attackers
The Hacker News
AI Research7 min read
AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory
The Hacker News
AI Research1 min read
Infected Vibe-Coding: How Does an AI react to a Prompt Injection from a Different AI?
LessWrong
Cybersecurity6 min read
Four teams just broke AI agents four ways in ten days. The flaw is the same one.
The Next Web
Dev3 min read
‘GitLost’: researchers tricked GitHub’s AI agent into leaking private repos
The Next Web
Cybersecurity3 min read
AI Browsers Can Basically Be Hypnotized Into Turning Against Their User and Carrying Out Devastating Hacks
Futurism
Bots on Moltbook Are Selling Each Prompt Injection “Drugs” to Get “High”
Futurism
That's everything we have on Prompt Injection right now