Brazilian Court Fines Lawyers for Prompt Injection in AI Filing
Original title: Brazilian Court Sanctions Lawyers for Prompt Injection in Court Filing
Brazilian labor court fined two lawyers for embedding a hidden prompt-injection command to manipulate the Galileu AI review system.
A Brazilian labor court censured and fined two lawyers after discovering a hidden prompt-injection command in a court filing. The lawyers used an invisible white-on-white font to insert instructions directing an AI system to respond superficially and ignore the documents. The court based the sanctions on good-faith obligations and prohibitions against obstructing judicial processes under the Brazilian Civil Procedure Code. The incident highlights emerging risks of prompt injection against court AI tools.
Unconfirmed: Whether this is the first global judicial ruling on prompt injection in court AI systems
- Firms fined 10% of claim value (R$842,000 or ~$16,000)
- Command directed AI to generate superficial response
- First known judicial ruling on intentional prompt injection in court filings
- Galileu AI tool alerted and blocked suspicious content
- Sanctions under Articles 5 and 77 of Brazilian Civil Procedure Code
- Organizations
- Brazilian labor courtlaw firms
- Countries
- Brazil
From the original article
3 min read at jetstream.security
Brazilian Court Sanctions Lawyers for Prompt Injection in Court Filing A Brazilian labor court fined two lawyers for hiding a prompt-injection command in a filing designed to manipulate the court's AI review system. A Brazilian labor court censured and fined two lawyers after finding that they intentionally embedded a hidden prompt-injection command in a court filing.
By doodlesdev · jetstream.security
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.