package-hallucination
Safeguard articles tagged "package-hallucination" — guides, analysis, and best practices for software supply chain and application security.
7 articles
Slopsquatting: When AI Hallucinates a Package Attackers Register
AI coding assistants confidently recommend packages that do not exist. Attackers noticed. Slopsquatting turns a model's hallucination into a supply-chain foothold — and the fix is not to make models stop hallucinating.
Slopsquatting: When AI Hallucinates Package Names
LLMs invent plausible package names; attackers register them and wait. How slopsquatting works, why hallucinations repeat predictably, and the gates that stop it.
How Copilot amplifies insecure codebases
Copilot writes ~46% of code where enabled, and studies show ~40% of its security-relevant suggestions are vulnerable. Here's the data on the risk.
Supply Chain Risks of AI Coding Assistants
Copilot, Cursor, and Claude Code change what enters your codebase and how. A practitioner's map of the real supply chain risks — hallucinated packages, rules-file injection, and unreviewed transitive trust.
GenAI Code Assistants and Package Hallucination: 2026 Update
LLM-suggested package names that do not exist are a registered attack vector in 2026. Here is where hallucination rates sit today and how to contain them.
Slopsquatting (AI package hallucination attack)
Slopsquatting exploits AI coding assistants that hallucinate nonexistent package names, which attackers then register as real, malicious packages.
AI Code Assistant Package Hallucination Study
The Safeguard Research team measured how often AI coding assistants hallucinate non-existent packages, how sticky those hallucinations are, and what defenders should do.