Executive Summary
Researchers describe HalluSquatting: registering project names that AI coding assistants tend to invent, so assistants may fetch attacker-controlled code.
What Happened
AI coding assistants have a habit of making things up. Ask one to fetch a popular tool, and it will sometimes hand back a real-sounding name for a project that does not exist. New research, which its authors call HalluSquatting, turns that habit into an attack: work out the fake names an AI reliably invents, register them first, and wait for the assistant to fetch your trap on a user's
Vulnerability / Attack Technique
Exploiting AI package hallucinations
Technical Mechanism
As reported, hallucinated names are registered by attackers in advance.
AI Security Category
LLM09:2025 Misinformation
Relevant Frameworks
RealGround Analysis
Hallucinations become supply chain risk when agents can install software. RealGround analysis: agents should not fetch tools without verification.
Recommended Controls
- Require approval before assistants install tools
- Verify project names against official sources
Related RealGround Service
AI Agent SBOM and LLM Mapping · or start with the free AI Agent Security Scanner.
Sources
thehackernews.com: https://thehackernews.com/2026/07/new-hallusquatting-attack-could-trick.html
Summary and analysis written by RealGround from the source above; last updated 2026-10-18.