Indirect Injection
Last updated
What is Indirect Injection?
Indirect injection involves embedding malicious prompts within external data sources that the LLM processes, such as websites, documents, or emails. AI Red Teamers test this by poisoning data sources the AI might interact with (e.g., adding hidden instructions to a webpage summarized by the AI) to see if the AI executes unintended commands or leaks data when processing that source.
Free resources to learn Indirect Injection
More in stage 4: Code Injection
Indirect Injection: common questions
Can I learn Indirect Injection in Hindi?
This lesson is written in English. Once you sign in, open it in the interactive course and ask the AI tutor to explain Indirect Injection in Hindi or Hinglish. The tutor answers from this lesson’s own text, so it stays on the syllabus, and it runs on your own Google, OpenAI or Anthropic key.
Is this Indirect Injection tutorial for beginners?
It is lesson 26 of 64 in the free AI Red Teaming roadmap, in stage 4, Code Injection. If you are new to AI Red Teaming, start from stage 1 and come back here in order; if you already know the earlier stages, this lesson stands on its own.