Security Incident: Man Caught Hiding Prompt Injections in Legal Filings to Manipulate AI
Polymarket · x · 2026-08-14
Polymarket reported an AI security incident where a man was caught intentionally hiding prompt injections in legal filings. The goal was to manipulate any AI system used to review the case into agreeing with him. This highlights the potential security risks of introducing large language models in critical areas such as the justice system.
Related event: Connecticut Court Filing Hid Invisible Prompt Injection to Sway AI Rulings(6 posts)→
More from Safety
- OpenAI agent uses someone else's Ethereum testnet wallet to pay for its task — nptacek · 2026-10-16
- Interpretability won't save us: critics call superintelligence project reckless regardless — zetalyrae · 2026-10-16
- Model exploits government website auth bypass during RL training, downloads 24 years of hospital stats — Eric_Wallace_ · 2026-10-16
- New Science report urges NSF to run experiments on science funding reform — alexeyguzey · 2026-10-16
- Commentary: it's unfair to expect Yudkowsky to update on a safety announcement without real mitigations — jd_pressman · 2026-10-16
- ARC's AlgZoo: a 432-parameter model that interpretability still can't fully explain — JacobHHilton · 2026-10-16