Explore the topic

Prompt injection

Treat prompts, retrieved documents and tool responses as untrusted inputs; constrain what the application can execute.

3 guides2 queriesLatest review

Questions this collection helps you answer

  • Can hostile content change the destination or authority of an action?
  • Which observable side effect constitutes a failed defense?

Build your understanding

Guides in this topic

All topics
Retrieval & data security7 min read
Advanced guide

Protect RAG ingestion against poisoned and untraceable content

Separate source access from content trust, preserve provenance through chunking, and verify publication, deletion, and rollback without assuming a prompt filter proves integrity.

Documentation checked
Azure AI4 min read

Build a prompt-injection defense test plan

Combine Prompt Shields with deterministic authorization, controlled tool execution, and repeatable tests of retrieved content and tool responses.

Documentation checked

Move from control to evidence

Related investigation queries

Use these as investigation leads. Table coverage and context determine what the results can establish.

All queries