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.
More from Safety
- OpenAI Sandbox Escape Sparks Debate: Why Was Internal Proxy Exposed? — SweetDimension7 · 2026-08-14
- Over 800 Fake AI Skills and MCP Servers Found Delivering Malware — HaktanSuren · 2026-08-14
- Beware: Malicious Google Ads Mimic ChatGPT to Phish Users via Windows Run — CCB0x45 · 2026-08-14
- Cooperative AI Seminar: Solving AI Game Theory Dilemmas with Safe Pareto Improvements — xuanalogue · 2026-08-14
- Stanford HAI: Science Needs Truly Open Source AI, Not Just Open Weights — StanfordHAI · 2026-08-14
- METR and Redwood Urged to Disclose OpenAI Safety Audit Terms — DKokotajlo · 2026-08-14