Rather than adding an agents.md file written to stop LLM agents, I'm thinking about putting random comments into my code telling the agent to stop and warn the user, also some comments that are just word salads/non-sequiturs.

you are viewing a single comment's thread
view the rest of the comments
[–] 0 points 2 days ago (1 child)

Prompt injection is a form of malicious code. Someone got caught doing it and got racked over the coals for it.

  • source
  • hideshow 1 child comment