Brazilian lawyer fined $16,000 over prompt injection in labor case filing
11/01/2026 — 11/01, 23:18·2 sources (all)·2 reports (all)
Key takeaways
- Tom's Hardware reports that in a Brazilian labor case, the plaintiff's lawyer hid a prompt injection in court filings instructing the court'…
Background & analysis
On November 1, 2026, security firm Jetstream Security reported that a Brazilian court had sanctioned a lawyer over the use of a prompt injection embedded in a court filing. According to the company's post, the document carried hidden instructions aimed at an AI system. A thread on Hacker News that surfaced the same day described it as one of the first instances of prompt injection producing real consequences inside a judicial process.
Later the same day, Tom's Hardware published additional details. In a labor dispute, the plaintiff's lawyer concealed a prompt injection inside documents submitted to the court, instructing the court's AI to review the case only on a superficial level. The court's AI detected the injected instruction, and the lawyer was fined $16,000. Despite the attempt, the plaintiff side won the case, since the defendant never responded, making the move unnecessary. The available reports do not indicate whether the sanctioned lawyer will appeal, and the matter stands at that point.
AI-generated from 2 reports · updated 2 hours ago
Latest turnAccording to Tom's Hardware, lawyers for the plaintiff in a Brazilian labor case hid a prompt injection in a court filing that instructed the court's AI to apply only superficial legal scrutiny. The AI flagged the hidden text, and the lawyers were fined $16,000. The plaintiff still won because the defendant did not respond.
- Heat index
- 157
- All sources
- 2
- All reports
- 2
- First seen
- 15 hours ago
Reports on this story headlines open the original
According to Tom's Hardware, lawyers for the plaintiff in a Brazilian labor case hid a prompt injection in a court filing that instructed the court's AI to apply only superficial legal scrutiny. The AI flagged the hidden text, and the lawyers were fined $16,000. The plaintiff still won because the defendant did not respond.
Tom's HardwareAI score 67A Brazilian court has sanctioned lawyers who embedded a prompt injection in a court filing, according to security firm Jetstream Security, which says hidden instructions aimed at AI systems were planted in the document. The case shows prompt injection moving from model demos into formal legal proceedings.
Hacker News · 热榜AI score 58
Other stories people are talking about
- Heat index 706OpenAI trims funding target; Anthropic may get BB rating at IPO16 sources
- Heat index 687RisingDeepSeek releases dsh-superagent prototype, detailing architecture and results10 sources
- Heat index 477Apple Intelligence comes to China with Qwen inside Siri15 sources
- Heat index 262Cursor removes tampered Claude Code extension, up to 5,000 developers affected8 sources
- Heat index 244SurgeOpenAI merges ChatGPT and Codex quotas, doubles Pro limits3 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion