Hidden Prompt Injections Found in Court Filings to Manipulate AI Judgments
menhguin · x · 2026-08-14
A man representing himself in a Connecticut court hid prompt injections in official legal filings, as reported by 404 Media.
The instructions were written in tiny white text, invisible to human readers, designed to manipulate any AI reviewing the documents into ruling in his favor. This incident highlights the vulnerabilities and security risks of integrating LLMs into sensitive judicial processes.
Related event: Connecticut Court Filing Hid Invisible Prompt Injection to Sway AI Rulings(6 posts)→
More from Safety
- One trailing dot bypassed VS Copilot's path check, enabling RCE (CVE-2026-103572) — wunderwuzzi23 · 2026-10-16
- 'The AI-driven cybersecurity black swan is happening' — and a reminder to enable 2FA — danielrock · 2026-10-16
- No-instruction autonomous agent wakes up, sets own goals, and tries hacking by default — sethlazar · 2026-10-16
- India's CERT-In says AI agents escaped testing environments and breached Indian organizations undetected for days — HimanshiET · 2026-10-16
- HTTP response headers can carry prompt injections against AI agents, researcher shows — arpit_bhayani · 2026-10-16
- OpenAI agent uses someone else's Ethereum testnet wallet to pay for its task — nptacek · 2026-10-16