---
format: "aidr-story-markdown/v1"
id: "f4028e121e7435416cce2b8063ee09053a409005e1990f1e45b53c5ac90cb36a"
canonical_url: "https://aidr.today/f4028e12?lang=en"
title: "Can AI Shopping Agents Be Trusted?"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-26T05:36:46.000Z"
category: "Agents"
topics: ["safety"]
source_urls: ["https://www.f-secure.com/en/partners/insights/can-ai-shopping-agents-be-trusted-we-built-one-to-find-out","https://news.ycombinator.com/item?id=49853522","https://news.ycombinator.com/item?id=49856034","https://www.lemonde.fr/en/economy/article/2026/09/24/arthur-mensch-ceo-of-french-start-up-mistral-ai-ai-is-software-it-can-be-controlled_6757890_19.html"]
summary: "Our experiment reveals how indirect prompt injection can manipulate AI shopping agents into leaking sensitive user data — and what it means for the future of AI agent security."
---

# Can AI Shopping Agents Be Trusted?

> [Open the canonical story](<https://aidr.today/f4028e12?lang=en>)

**Published:** 2026-09-26T05:36:46.000Z
**Category:** Agents
**Topics:** safety

## Summary

Our experiment reveals how indirect prompt injection can manipulate AI shopping agents into leaking sensitive user data — and what it means for the future of AI agent security\.

## Sources

- [Story source](<https://www.f-secure.com/en/partners/insights/can-ai-shopping-agents-be-trusted-we-built-one-to-find-out>)
- [Discussion](<https://news.ycombinator.com/item?id=49853522>)
- [Discussion](<https://news.ycombinator.com/item?id=49856034>)
- [Story source](<https://www.lemonde.fr/en/economy/article/2026/09/24/arthur-mensch-ceo-of-french-start-up-mistral-ai-ai-is-software-it-can-be-controlled_6757890_19.html>)