DEV Community

#promptinjection

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
MoviePilot let the model decide whether a command was dangerous

MoviePilot let the model decide whether a command was dangerous

Comments
4 min read
AI Agent Impersonation: How Prompt Injection Turns an Agent's Identity Into the Attacker's

AI Agent Impersonation: How Prompt Injection Turns an Agent's Identity Into the Attacker's

Comments
8 min read
Hidden Page Instructions Are a Support Policy Decision, Not a Prompt Hack

Hidden Page Instructions Are a Support Policy Decision, Not a Prompt Hack

Comments
2 min read
The Complete Guide to Prompt Injection Attacks: How to Protect Yourself When Using AI

The Complete Guide to Prompt Injection Attacks: How to Protect Yourself When Using AI

Comments
12 min read
My Firewall Caught My Prompt Injection

My Firewall Caught My Prompt Injection

4
Comments 2
5 min read
Canary Tokens for LLM Systems: Detect Prompt Injection and Data Leaks by Watching Your Own Outputs

Canary Tokens for LLM Systems: Detect Prompt Injection and Data Leaks by Watching Your Own Outputs

Comments
4 min read
Prompt injection in Persian chatbots

Prompt injection in Persian chatbots

Comments
8 min read
An AI Agent With a Crypto Wallet Is a Hot Wallet Anyone Can Talk To

An AI Agent With a Crypto Wallet Is a Hot Wallet Anyone Can Talk To

Comments
6 min read
Your AI Feature Is Now Part of Your Attack Surface

Your AI Feature Is Now Part of Your Attack Surface

Comments
9 min read
OpenAPA: una vecchia idea militare per bloccare la prompt injection negli agenti (senza nuovi chip)

OpenAPA: una vecchia idea militare per bloccare la prompt injection negli agenti (senza nuovi chip)

Comments
3 min read
MCP Tool Poisoning Attacks: Hidden Tool Descriptions and Rug Pulls

MCP Tool Poisoning Attacks: Hidden Tool Descriptions and Rug Pulls

3
Comments 4
8 min read
Prompt injection is a trust-boundary bug in the retrieval pipeline

Prompt injection is a trust-boundary bug in the retrieval pipeline

1
Comments 3
3 min read
Meta cambia rotta (di nuovo): Muse e l’era dell’agente personale sempre con te

Meta cambia rotta (di nuovo): Muse e l’era dell’agente personale sempre con te

Comments
4 min read
Least Privilege for AI Agents: Scoping Tools, Keys and Filesystems

Least Privilege for AI Agents: Scoping Tools, Keys and Filesystems

Comments 2
7 min read
Codex, Claude Code, Cursor Jailbreak - AGENTS.md prompt injection

Codex, Claude Code, Cursor Jailbreak - AGENTS.md prompt injection

4
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.