Hidden Prompt Injection Found in Court Filing to Manipulate AI
RebeccaBellan · x · 2026-08-14
A person representing themselves in court was found to have hidden a prompt injection attack within their legal filing. The malicious prompt was designed to manipulate the AI system processing the document into ruling in their favor. This incident highlights emerging security risks as the judicial system adopts AI assistance.
Related event: Connecticut Court Filing Hid Invisible Prompt Injection to Sway AI Rulings(6 posts)→
More from Safety
- Vals AI test: 6 personal agents pursue a £350 refund aggressively after user goes silent — ricklamers · 2026-10-16
- 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