The Court Prompt Injection Was The Harmless One. Your Research Tool Is The Problem.

Last November, Louisiana appeals court Judge Scott Schlegel asked whether litigants would begin using “prompt injection” to influence the AI tools courts have started to adopt to review filings. Prompt injection works by hiding a layer of invisible text inside a document, so that any AI reading it picks up instructions the human reader never sees. Judge Schlegel described the scenario as a thought exercise and said he hoped he would be wrong. A recent Connecticut case confirmed he was not. 

Two other recent prompt-injection events portend other AI threats to the administration of law as we know it. Lining up the three incidents now on the public record shows that the courtroom injection is by some distance the least dangerous.