{
  "id": 17625886,
  "title": "Brazilian lawyers busted for attempting to manipulate court's AI with prompt injection hidden in filing",
  "url": "https://urgent.news/2026/11/01/brazilian-lawyers-busted-for-attempting-to-manipulate-courts-ai-with",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-01T15:05:00.000Z",
  "source": {
    "name": "Tom's Hardware",
    "slug": "tom-s-hardware",
    "url": "https://www.tomshardware.com/tech-industry/artificial-intelligence/brazilian-lawyers-busted-for-attempting-to-manipulate-courts-ai-with-prompt-injection-hidden-in-filing-courts-ai-flags-hidden-text-that-demanded-superficial-legal-scrutiny-lawyers-fined-usd16-000"
  },
  "original_language": "en",
  "account": "In a recent case, two Brazilian lawyers were penalized for their attempt to manipulate the court's AI system through a technique known as prompt injection. The lawyers, Prof. Vladimir Aras of the University of Brazil and an unnamed colleague, included hidden instructions in white font on a white background within their filing. This text was designed to trick the AI system into responding in a manner favorable to the lawyers, while remaining invisible to human readers. Despite the court's attempt to dismiss the case due to the defendants' lack of technical knowledge, the lawyers were still fined 10% of the award, approximately $16,000, for their offensive act towards the dignity of justice.",
  "summary": "The lawyers of a plaintiff in a labor case attempted to use prompt injection to influence the court's AI but were caught. They won the case anyway, as the defendant did not respond, making the move totally unnecessary.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}