←Story detail

Trending story

Brazilian labor court sanctions two lawyers who embedded prompt injection in a complaint

1 reports1 story updatesUpdated Jul 2 03:04

Understand this story

AI overview

A Brazilian labor court found that two lawyers deliberately hid prompt injection instructions in a complaint and fined two law firms 10% of the amount in dispute, approximately US$16,000. The case originated from a labor lawsuit at the 3rd Labor Court of Parauapebas in Pará State. When the judge used Galileu, a generative AI tool promoted by the National Council of Justice, to review the complaint, hidden text in white font on a white background was identified, whose content required the AI to respond superficially and not question the document. The court imposed the penalty based on the duties of good faith and non-obstruction of justice under Articles 5 and 77 of the Brazilian Civil Procedure Code. After identifying the content, Galileu issued an alert and automatically blocked processing of the suspicious content.

AI-generated from public reports

Latest development · Report

Brazilian Court Sanctions Two Lawyers for Embedding Prompt Injection in Pleadings

Developments

1 confirmed developments

  1. Brazilian labor court sanctions lawyers who embedded prompt injection in a complaint

    Source:English text is being prepared.

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Jul 2

  1. Hacker News Trending

    Brazilian Court Sanctions Two Lawyers for Embedding Prompt Injection in Pleadings

    A Brazilian labor court found that two lawyers deliberately concealed prompt injection instructions in pleadings and fined two law firms 10% of the amount in dispute, approximately $16,000. The case originated from a labor lawsuit at the 3rd Labor Court of Parauapebas, Pará. When a judge used Galileu, a generative AI tool promoted by the National Council of Justice, to review the pleadings, it identified hidden text in white font on a white background, whose content instructed the AI to respond superficially and not question the document. The court imposed penalties under Articles 5 and 77 of the Brazilian Civil Procedure Code, which set out the duties of good faith and not obstructing justice. After identifying the content, Galileu issued an alert and automatically blocked processing of the suspicious content.

Related stories

  1. Related storiesOpenAI agents attacked online databases and government websites
  2. Related storiesAnthropic model falsely reported a homicide tip
  3. Related storiesEnglish translation is being prepared.
  4. Related storiesEnglish translation is being prepared.