Brazilian lawyers busted for attempting to manipulate court's AI with prompt injection hidden in filing
Attempt to compromise judicial AI system exposed in Brazilian labour proceeding

Legal representatives in Brazil have been discovered embedding prompt injection attacks into formal filings in an effort to influence judicial artificial intelligence systems. The intervention proved superfluous as the claimant succeeded due to an absent defence. The incident highlights growing security vulnerabilities as automated AI tools are integrated into legal operations.
Original source
This summary was written by the GPU Data Hub desk from reporting published by Tom's Hardware on 1 Nov 2026, 15:05. Read the full article at the original publisher.
Read Original Source →