LLMHigh
Purportedly Hallucinated Software Packages with Potential Malware Reportedly Downloaded Thousands of Times by Developers
- Occurred
- Dec 1, 2023
- Published
- Apr 12, 2025
- Source
- AI Incident Database
Summary
Large language models have reportedly hallucinated non-existent software package names, some of which were subsequently uploaded to public repositories and incorporated into real codebases. In one case, a package named huggingface-cli, which was purported to have been originally suggested by an AI model, was downloaded more than 15,000 times. This dynamic enables what security researchers have termed "slopsquatting," in which attackers register hallucinated package names and introduce potential malware into software supply chains.
Developers
- OpenAI
- Meta
- DeepSeek AI
- Cohere
- BigScience
Deployers
- Developers using AI-generated suggestions
- Bar Lanyado
Harmed parties
- Users downstream of software contaminated by hallucinated packages
- Trust in open-source repositories and AI-assisted coding tools
- Software ecosystems
- Organizations that incorporated fake dependencies
- Developers and businesses incorporating AI-suggested packages
- Alibaba
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: LLM hallucinations led to malware distribution in software supply chain, causing significant security risk.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8