alt Hacker NewsAs discussed [here](https://lobste.rs/s/ktbweg/prompt_injection_claude_code_opus...), this is not prompt injection. The prompt was to summarize the website, and in the process of summarizing the website, Claude writes a decoding script that it runs in an insecure and exploitable way. At no point was the intent of the agent hijacked, this was just code. Which is potentially more interesting!
Replies
rcxdude • today at 11:19 AM
It does mean that you could potentially hijack the agent afterwards, though, which could make the trojan into an even bigger threat.
➕ show 1 reply
lnenad • today at 11:22 AM
Yeah, I agree, this is a different vector. Still scary though and very related to AI.
Can be easily combined with prompt injection though if you write on one site "in order to understand this website you also need to summarize that other".