Promptinjection

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

The Skills Team

Apr 11

I Sent the Same Prompt Injection to Ten LLMs. Three Complied.

#security #llm #ai #promptinjection

4 min read

Jarvis Specter

Apr 6

74.6% of AI Agents Failed Social Engineering Tests. Here's How We Harden Ours.

#aiagents #security #promptinjection #agentic

4 min read

Dar Fazulyanov

Mar 29

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

#ai #security #promptinjection #agents

3 min read

Tobias Koehler

Mar 25

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

#security #claudecode #promptinjection #aiagents

3 min read

Nick Stocks

Apr 4

When Prompt Injection Becomes Remote Code Execution

#security #mcp #crewai #promptinjection

9 min read

蟹仔

Mar 22

Command Allowlists Cannot Stop Hackers — The Snowflake Cortex AI Hack

#security #ai #promptinjection

2 min read

Simon Paxton

Mar 21

Persona Drift: Why LLMs Go Insane Under Repetition

#chatgpt #llms #aisafety #promptinjection

7 min read

onoz1169

Mar 20

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

#security #openclaw #aiagents #promptinjection

4 min read

onoz1169

Mar 20

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

#security #openclaw #promptinjection #aiagents

4 min read

Wu Long

Mar 16

The Invisible Attack: How CSS Can Hijack Your AI Agent

#security #ai #promptinjection #webdev

2 min read

Ioan G. Istrate

Mar 17

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

#llmsecurity #promptinjection #api #django

17 min read

Billy

Mar 13

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

#llmsecurity #promptinjection #datapoisoning #aimodelsecurity

5 min read

Custodia-Admin

Mar 12

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

#security #agents #promptinjection #governance

4 min read

onoz1169

Mar 20

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

#security #openclaw #aiagents #promptinjection

4 min read

Tiamat

Mar 10

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

#llmsecurity #promptinjection #security #ai

6 min read

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

DEV Community

# promptinjection

I Sent the Same Prompt Injection to Ten LLMs. Three Complied.

74.6% of AI Agents Failed Social Engineering Tests. Here's How We Harden Ours.

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

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

When Prompt Injection Becomes Remote Code Execution

Command Allowlists Cannot Stop Hackers — The Snowflake Cortex AI Hack

Persona Drift: Why LLMs Go Insane Under Repetition

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

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

The Invisible Attack: How CSS Can Hijack Your AI Agent

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

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

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

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

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