Man injected invisible prompts in court filings to influence AI systems
jonippolito · x · 2026-08-16
A Connecticut judge has identified what appears to be the first instance of a plaintiff attempting to hide text in court filings that only an AI system can read. The goal was to manipulate any AI tools reviewing the document to agree with the plaintiff's arguments.
Judge Walter Spader Jr. confirmed that the hidden text—formatted to be invisible to humans but legible to software—had no impact on the case's outcome. However, the judge warned that this sets a dangerous precedent. As AI tools become more integrated into court systems, such malicious tactics are likely to become more common.
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