# Preprint tests coordinated search-result attacks on AI agents

_Tuesday, August 25, 2026 at 12:00 AM EDT · Science, Security · Latest · Tier 2 — Notable_

A new arXiv preprint reports that a controlled search intermediary can steer LLM-based search agents by inserting one result per query and coordinating evidence across an agent's research path.

The authors describe their Authority-Chain Hijack method as reaching 55.9% attack-success rate and 83.3% MaxN attack-success rate on the full SafeSearch test split. A trace-guided strategy system reached 71.4% and 95.0%, respectively, in held-out evaluation. The work frames search and page-observation channels as a security boundary rather than only a source of isolated prompt injections.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2608.04565)

---
Canonical: https://techandbusiness.org/newswire/DC80V3PR_vT-ic5W38OqXw
Retrieved: 2026-08-26T20:46:06.051Z
Publisher: Tech & Business (techandbusiness.org)