Analysis · curated 16 Sep 2026
Should I Be Worried About Prompt Injection? – Louisiana Legal Ethics
First reported lalegalethics.org
Coverage timeline
Single-source analysis — first reported, latest, and curated coincide.
Why it matters
Indirect prompt injection via hidden text in documents is a recognized security risk for AI tools that review third-party files, and this piece shows current major LLMs often detect the simple white-font variant while cautioning that tool-enabled agents remain more exposed.
An analysis for Louisiana lawyers examines indirect prompt injection after a self-represented litigant, Matthew Elliott, hid white-font instructions in a Connecticut court filing telling any reviewing AI to side with him; the court was not using AI, and the judge revoked his e-filing privileges. The authors ran their own informal test embedding a hidden instruction in a motion and found that Claude, Perplexity, and ChatGPT each detected and refused the injected instruction.