Threat
Brazilian lawyers busted for attempting to manipulate court's AI with prompt injection hidden in filing — court's AI flags hidden text that demanded superficial legal scrutiny, lawyers fined $16,000
First reported tomshardware.com
Page published
Earliest dated coverage: 1 Nov 2026 · First observed: 1 Nov 2026 · Latest dated coverage: 1 Nov 2026
Coverage timeline
Single-source incident — one report is available.
Why it matters
The reported court-filing attack shows how adversarial documents can carry hidden instructions intended to redirect AI-assisted review in consequential workflows.
Brazilian lawyers reportedly hid prompt-injection instructions in a court filing to induce superficial legal scrutiny by the court's AI. According to the headline, the AI flagged the hidden text and the lawyers were fined $16,000; successful manipulation is not reported.