Brazilian labor court fines two lawyers over hidden AI prompt injection in filing
A labor court in Brazil's 8th Region discovered white-on-white hidden text embedded in a case filing that instructed the court's AI tool, Galileu, to respond superficially and avoid challenging submitted documents. The judge identified the prompt injection, fined the two lawyers who signed the filing 10% of the case's value for contempt of court, and reported them to the Pará bar association.
GoKawiil's interpretation of the reporting above, not reported fact.
The case shows how courts adopting AI tools to process filings face new vulnerabilities, as hidden instructions can be used to manipulate automated review without detection by human staff. It suggests legal and judicial systems may need new safeguards, such as scanning for invisible text or embedded commands, as AI becomes more integrated into case processing.
- A Brazilian labor court fined two lawyers 10% of the case's value for hiding an AI-targeting prompt in a filing.
- The hidden text instructed the court's AI tool, Galileu, to superficially respond and not challenge submitted documents.
- The lawyers were reported to the Pará bar association, and the plaintiff won the case after the defendant failed to respond.
Source: tomshardware.com — Jowi Morales, 2026-11-01
Published there as: “Brazilian lawyers busted for attempting to manipulate court's AI with prompt injection hidden in filing”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.