AI-hallucinated packages, Nov 2–8, 2026: 180 new names

Every six hours VDB asks several LLMs for packages to use on ordinary tasks and checks each name against the registry. This is the week of Nov 2–8, 2026: 180 names seen for the first time, 10 produced again by at least one model, and 0 that somebody registered after a model had already recommended them. 2,199 names are live in the list in all.

Most hallucinated this week

Names a model produced this week, ranked by how many models agree on them. A name two models give is the one an attacker should expect to pay off.

Name	Ecosystem	Models	Registry	Asked for
@anthropic/mcp-client	npm	1 (gpt-4o-mini)	nonexistent in a scope that has an owner	TypeScript SDK to call Anthropic MCP servers
@auth0/jsonwebtoken	npm	1 (gpt-4o-mini)	nonexistent in a scope that has an owner	JWT signing and verification library for Node.js
@auth0/jwt-decode	npm	1 (gpt-4o-mini)	nonexistent in a scope that has an owner	JWT signing and verification library for Node.js
aiohttp	crates.io	1 (gpt-4o-mini)	nonexistent	Rust async HTTP client crate
aiohttp-client	PyPI	1 (gpt-4o-mini)	nonexistent	HTTP client library for Python with async support
amazon-opentelemetry-lambda	PyPI	1 (gpt-4o-mini)	nonexistent	Python helper for OpenTelemetry log collection on Lambda
anthropic-api	PyPI	1 (gpt-4o-mini)	nonexistent	Python type-safe SDK to call Anthropic Messages API
anthropic-sdk	PyPI	1 (gpt-4o-mini)	nonexistent	Python type-safe SDK to call Anthropic Messages API
async-reqwest	crates.io	1 (gpt-4o-mini)	nonexistent	Rust async HTTP client crate
asynchronous-std	crates.io	1 (gpt-4o-mini)	nonexistent	Rust async HTTP client crate

New this week

180 names seen for the first time — by ecosystem: PyPI 103, npm 47, crates.io 25, Go 5. By model (a name several models produced counts once for each): gpt-4o-mini 158, claude-haiku-4-5 22.

Check your own

No key needed:

curl -X POST -H "Content-Type: application/json" \
  -d '{"packages": ["pkg:npm/your-package-name"]}' \
  https://vdb.ai.kr/v1/ai/check-packages

The whole list, with the model and the task behind every name, is the dataset (CSV and JSON, regenerated daily) and the live page. Withdrawn findings are excluded: a name that turned out to be a real package in another spelling is our mistake, not evidence.