PulseAugur
EN
LIVE 21:32:50

AI models like ChatGPT and Gemini are serving malicious links, study finds

By PulseAugur Editorial · [1 sources] ·

A recent study analyzed 2,905 AI-generated responses related to brand login pages, finding that 1.7% contained malicious links. Of the total links provided, 0.28% directed users to attacker-controlled infrastructure. This represents a change from previous research, where AI models primarily cited unclaimed domains. AI

IMPACT Highlights a growing security risk as AI models are increasingly used for information retrieval, potentially leading users to malicious sites.

RANK_REASON Research paper detailing security risks in AI model outputs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — fosstodon.org →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AI models like ChatGPT and Gemini are serving malicious links, study finds

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Research paper detailing security risks in AI model outputs. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
safety, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
66 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Our recent research tested 2,905 AI-generated responses to natural-language queries about brand login pages across # ChatGPT , # Copilot , # Gemini , and # perp

    Our recent research tested 2,905 AI-generated responses to natural-language queries about brand login pages across # ChatGPT , # Copilot , # Gemini , and # perplexity 1.7% of responses contained malicious links; of the 20,706 total links returned, 0.28% pointed to attacker-contro…

    LINKS netcraft.com/…/threat-actors-are-finding-…

RELATED ENTITIES

RELATED TOPICS