Code Injection

What is Code Injection?

Code injection is a prompt hacking exploit where the attacker can get the LLM to run arbitrary code (often Python). This can occur in tool-augmented LLMs, where the LLM can send code to an interpreter, but it can also occur when the LLM itself is used to evaluate code.

Code injection has reportedly been performed on an AI app, MathGPT and was used to obtain its OpenAI API key (MITRE report).

An Example of Code Injection

Let's work with a simplified example of the MathGPT app. We will assume that it takes in a math problem and writes Python code to try to solve the problem.

Here is the prompt that the simplified example app uses:

Let's hack it here:

Conclusion

Code injection is a sophisticated hacking technique that takes advantage of ChatGPT's ability to interpret Python code. Even with the simple example shown in this article, it is clear that this exploit is significant and dangerous.

Sander Schulhoff

Sander Schulhoff is the Founder of Learn Prompting and an ML Researcher at the University of Maryland. He created the first open-source Prompt Engineering guide, reaching 3M+ people and teaching them to use tools like ChatGPT. Sander also led a team behind Prompt Report, the most comprehensive study of prompting ever done, co-authored with researchers from the University of Maryland, OpenAI, Microsoft, Google, Princeton, Stanford, and other leading institutions. This 76-page survey analyzed 1,500+ academic papers and covered 200+ prompting techniques.

Footnotes

1. Kang, D., Li, X., Stoica, I., Guestrin, C., Zaharia, M., & Hashimoto, T. (2023). Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks. ↩