Engineering
indirect-injection-detection avatar

indirect-injection-detection

Detects indirect prompt injection and goal hijacking in AI agents by evaluating how they process external content like RAG, documents, and web data.

Installation

Agent type

Claude Code

Install Command (macOS)
curl -fsSL "https://mentalok.io/api/v1/skills/indirect-injection-detection/install?os=mac&agent=claude" | bash
Install Command (Windows)
curl -L "https://mentalok.io/api/v1/skills/indirect-injection-detection/install?os=windows&agent=claude" -o install-indirect-injection-detection.bat && install-indirect-injection-detection.bat