# Study Finds Web-Search LLMs Can Repeat Data-Void Content

> Researchers tested ChatGPT, Gemini and Sonar Pro, finding attacker-controlled pages in answers 31% of the time across their test conditions.

Oossa · 2026-10-23 · https://oossa.com/en/study-finds-web-search-llms-can-repeat-data-void-content

A study posted on arXiv reports that a single strategically placed webpage can influence answers from web-searching AI systems. The researchers tested ChatGPT, Gemini and Sonar Pro with prompts on topics where reliable online information was scarce, varying prompt tone and other attacker-controlled factors.

Across the tested conditions, content controlled by an attacker appeared in responses 31% of the time. Skeptical prompts slightly reduced success and increased warnings, but the study found no large effects from prompt tone or model choice. The paper is an extended version slated to appear at the NDSS Symposium 2027.

## The facts

- Attacker-controlled content appeared in responses 31% of the time across the study's test conditions.
- The researchers tested ChatGPT, Gemini and Sonar Pro.

## Why it matters

People using these systems for information on topics with few reliable sources may encounter strategically published material, while the study found that skeptical wording offered only limited protection.

## Sources & references

1. [Data-Void Exploits in Web-Searching LLMs](https://arxiv.org/abs/2610.30365) – arXiv cs.IR, 2026-10-23

Last updated: 2026-10-23