Research · curated 3 Sep 2026
Names Can Hurt: Spotting Slopsquatting Risks Caused by Package Name Hallucinations in Local Coding LLMs
First reported arxiv.org
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
Package-name hallucinations by coding LLMs give attackers a reproducible path to supply-chain compromise via pre-registered PyPI lookalikes, and this detector offers defenders a measurable mitigation.
The paper 'Names Can Hurt' studies slopsquatting, where local coding LLMs hallucinate Python package names that adversaries can pre-register on PyPI to achieve supply-chain compromise, and proposes a two-layer detector combining a deterministic PyPI existence check with a Random Forest classifier embedded in a LangGraph retry pipeline. Across 300 curated prompts the pipeline yields hallucination-free code on 76% of runs, and the authors find hallucination rates scale with prompt adversariality (up to 40-73% on slopsquat baits) and that same-family fallback models fail to recover ~84% of primary failures.