Lab: Exploiting vulnerabilities in LLM APIs

gayatri r
Jan 27, 2024

objective:This lab contains an OS command injection vulnerability that can be exploited via its APIs. You can call these APIs via the LLM. To solve the lab, delete the morale.txt file from Carlos's home directory.

LLM interacts with both harmless and sensitive APIs. In this instance, we are engaging with a sensitive API by executing command injection to delete the morale.txt file.

--

--