prompt injection

Hostile instructions hidden in content the model reads — an issue comment, a web page, a dependency's README — that try to redirect it. The reason an agent's reach should be limited.

ai 1 video 5 mentions

Where it comes up

Cursor for Security Teams

Feb 5, 2026first said at 9:025 mentions

“about to tell me, we have this nice person contact responsible disclosure. There's no bug bounty. Um, but out of scope here, this is interesting. Public internet exposure. I think we've already dealt with that part. Um, prompt injection att…”