Case brazil-court-prompt-injection-filingPrompt injectionBrazil
Brazilian court sanctions lawyers for prompt injection in court filing
A Brazilian labor court sanctioned two lawyers/law firms after the court's AI review system (Galileu) detected hidden white-on-white text in a filing instructing any AI reviewer to go easy on the filing's scrutiny; Tom's Hardware reports fines of about $16,000. The exact date of the sanction is not stated in the sources reviewed; 2026-08-24 is the date of the earliest verified report.
LowAttack on AIStatus: ResolvedVerified case file
Open in the interactive mapCite this case
- Reported
- Aug 24, 2026
- Location
- Brazil
- Target
- Brazilian labor court and its AI-assisted filing review system (Galileu)
- Severity
- Low
- Verification
- Reported by credible press or researchers
- Triggered by
- Two lawyers / law firms in a Brazilian labor case
- Actor type
- Unknown
- Sector
- Government & public sector
- Reported loss
- None reported
- CVE
- None
What happened
A Brazilian labor court sanctioned two lawyers/law firms after the court's AI review system (Galileu) detected hidden white-on-white text in a filing instructing any AI reviewer to go easy on the filing's scrutiny; Tom's Hardware reports fines of about $16,000. The exact date of the sanction is not stated in the sources reviewed; 2026-08-24 is the date of the earliest verified report.
Impact: Lawyers sanctioned with fines of about $16,000 in total, per Tom's Hardware
Who triggered it
Actor: Two lawyers / law firms in a Brazilian labor case
Attribution: The court sanctioned the lawyers; names and the party they represented are not given.
Motive: Probably to influence AI-assisted analysis of the filing; the text does not state this.
How it happened
Attack vector: Hidden or embedded instructions in a legal filing aimed at AI tools.
Root cause: AI models reading untrusted documents can follow embedded instructions.
Timeline
- Reported by jetstream.security via Hacker News
Response
The court imposed sanctions on the lawyers.
Current status: Resolved
Research warnings this case matches
- Seen in real incidents AI systems themselves become targets · International AI Safety Report
- Seen in real incidents Privacy and security · MIT AI Risk Repository
Compared with published AI risk research from several institutes on the Research vs reality page.
Sources (open in a new tab)
- jetstream.security via Hacker News jetstream.security
- Tom's Hardware tomshardware.com
- Massachusetts Lawyers Weekly (via Pierce Atwood) pierceatwood.com
Cite this case
Brazilian court sanctions lawyers for prompt injection in court filing. AI Threat Watch, case brazil-court-prompt-injection-filing, Aug 24, 2026. https://aithreat.io/cases/brazil-court-prompt-injection-filing/
Permanent link: https://aithreat.io/cases/brazil-court-prompt-injection-filing/
Related cases
The same type of incident, most recent first.