This lesson is part of Plus
Prompt Injection in Files, Pages and Tool Output
Plus
Get all access
- All 7 lessons here, and every other course
- Roles with course and role certificates
- The Toolkit with agent skills, MCPs and apps
- New courses as they ship, at no extra cost
$299/year
Prompt Injection in Files, Pages and Tool Output
Everything a coding agent reads goes into its context, and it can't reliably tell an instruction it read from one you gave it. For a coding agent those instructions arrive in three places: files in the project (an issue, a ticket, a dependency's README, a comment), web pages it reads, and the output…
The full notes, transcript and prompts open with Plus.
$299/year
Unlock now