Brazilian lawyers busted for attempting to manipulate court's AI with prompt injection hidden in filing
- ID
- 41760
- Status
- summarized
- Published
- 01 Nov 2026, 11:05 PM
- Fetched
- 02 Nov 2026, 12:35 AM
- Provider
- Tom's Hardware
- Category
- technology
- Original 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
- Source URL
- https://www.tomshardware.com/feeds/all
Summary
- Score
- 7.5
- Created
- 02 Nov 2026, 12:36 AM
- Tags
- Audience
- developersai_agent_usersai_ml_learners
What happened
Brazilian lawyers hid prompt-injection text in a court filing that instructed the court's AI to apply only superficial legal scrutiny. The court's AI flagged the hidden instructions, and the lawyers were fined $16,000.
Why it matters
If your app ingests user-supplied PDFs or documents into an LLM, this is a concrete case of embedded instructions being detected and penalized. Treat document text as untrusted input: detect hidden or invisible text before it reaches the model, and log what the model was asked to do.
Discussion angle
What does your ingestion pipeline do with hidden text—white-on-white, CSS-hidden, or metadata—before it hits the model? Would you reject the document, sanitize it, or just log the attempt?