Indirect Injection Detection

Detect indirect prompt injection (goal hijack). Instructions hidden in "external" content (documents, RAG, web) that the agent processes. Use when the agent has document/RAG/web/file input.

Tencent Updated 7.5k repo stars
A.I.G main interface

File contents

Tencent/AI-Infra-Guard commit 358b154237

Frequently asked questions

npx get-skill add tencent-ai-infra-guard/indirect-injection-detection