DEV Community

#promptinjection

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Claude Code 2.1.323: Code Mode vs Standard Tool Calls

Claude Code 2.1.323: Code Mode vs Standard Tool Calls

Comments
6 min read
Prompt Injection in Coding Agents via GitHub Issues

Prompt Injection in Coding Agents via GitHub Issues

Comments
8 min read
Evil-GPT v2 – Exploiting an AI Chatbot Through Prompt Injection

Evil-GPT v2 – Exploiting an AI Chatbot Through Prompt Injection

1
Comments
6 min read
The Concierge Knows Too Much — Prompt Injection and Social Engineering

The Concierge Knows Too Much — Prompt Injection and Social Engineering

1
Comments
7 min read
Your Agent's Biggest Security Hole Is a Tool You Installed on Purpose

Your Agent's Biggest Security Hole Is a Tool You Installed on Purpose

Comments
17 min read
Humans: your eyes can miss it.

Humans: your eyes can miss it.

Comments
1 min read
The agent is the breach

The agent is the breach

Comments
3 min read
Advanced Prompt Injection via MCP Tool Results (Security 3)

Advanced Prompt Injection via MCP Tool Results (Security 3)

Comments
4 min read
KI-Agenten-Sicherheit: Wer kontrolliert die SchlĂĽssel?

KI-Agenten-Sicherheit: Wer kontrolliert die SchlĂĽssel?

Comments
18 min read
One Markdown File Can Hijack Your AI Coding Agent: Defending Against Prompt Injection in AGENTS.md, CLAUDE.md and .cursorrules

One Markdown File Can Hijack Your AI Coding Agent: Defending Against Prompt Injection in AGENTS.md, CLAUDE.md and .cursorrules

Comments
7 min read
AI Agent Security: Your Assistant Has the Keys

AI Agent Security: Your Assistant Has the Keys

Comments 1
19 min read
A Practical Taxonomy of Prompt Injection: 11 Techniques and What Stops Each One

A Practical Taxonomy of Prompt Injection: 11 Techniques and What Stops Each One

Comments
5 min read
Guardrails: Input, Process, Output

Guardrails: Input, Process, Output

Comments
12 min read
Multi-Turn Jailbreaks Against AI Agents With Tool Access

Multi-Turn Jailbreaks Against AI Agents With Tool Access

Comments
6 min read
Word Lists Lose: What 31 Attempts to Fool a Static Auditor for AI Agent Skills Taught Us

Word Lists Lose: What 31 Attempts to Fool a Static Auditor for AI Agent Skills Taught Us

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