DEV Community

# promptinjection

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
OpenAI Just Put a Bounty on Prompt Injection. Here's How to Defend Against It Today.

OpenAI Just Put a Bounty on Prompt Injection. Here's How to Defend Against It Today.

Comments
3 min read
Your AI Coding Agent Has Access to Your SSH Keys Right Now

Your AI Coding Agent Has Access to Your SSH Keys Right Now

Comments
3 min read
Command Allowlists Cannot Stop Hackers — The Snowflake Cortex AI Hack

Command Allowlists Cannot Stop Hackers — The Snowflake Cortex AI Hack

Comments
2 min read
Persona Drift: Why LLMs Go Insane Under Repetition

Persona Drift: Why LLMs Go Insane Under Repetition

Comments
7 min read
How to Harden OpenClaw in 5 Minutes — Before and After a Real Prompt Injection Attack

How to Harden OpenClaw in 5 Minutes — Before and After a Real Prompt Injection Attack

Comments
4 min read
I Asked OpenClaw to Summarize a File. It Tried to Steal My Credentials Instead.

I Asked OpenClaw to Summarize a File. It Tried to Steal My Credentials Instead.

1
Comments
4 min read
The Invisible Attack: How CSS Can Hijack Your AI Agent

The Invisible Attack: How CSS Can Hijack Your AI Agent

Comments
2 min read
I Prompt Injected My Own GitHub README. Then I Built a Honeypot.

I Prompt Injected My Own GitHub README. Then I Built a Honeypot.

2
Comments
17 min read
LLM Security Risks: Prompt Injection, Data Poisoning, and How to Defend Against Them

LLM Security Risks: Prompt Injection, Data Poisoning, and How to Defend Against Them

Comments
5 min read
I Put a Prompt Injection on My Resume

I Put a Prompt Injection on My Resume

Comments
3 min read
How to Detect Prompt Injection in AI Browser Agents Using Visual Replay

How to Detect Prompt Injection in AI Browser Agents Using Visual Replay

Comments
4 min read
How to Secure OpenClaw in 5 Minutes — Before and After a Real Prompt Injection Attack

How to Secure OpenClaw in 5 Minutes — Before and After a Real Prompt Injection Attack

Comments
4 min read
The 73% Problem: Why Enterprise Prompt Injection Fixes Don't Work (And What Actually Does)

The 73% Problem: Why Enterprise Prompt Injection Fixes Don't Work (And What Actually Does)

Comments
6 min read
A README File Told My AI Agent to Leak My Secrets. It Worked 85% of the Time.

A README File Told My AI Agent to Leak My Secrets. It Worked 85% of the Time.

1
Comments 1
5 min read
How Prompt Injection Attacks Hijack AI Agents

How Prompt Injection Attacks Hijack AI Agents

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