{"id":"modelscan","name":"ModelScan","maker":"Protect AI","url":"https://github.com/protectai/modelscan","repo":"protectai/modelscan","package":"pypi:modelscan","summary":"A command-line scanner that checks saved machine learning model files for unsafe serialised code.","details":"Looks inside model files in formats such as pickle, H5 and SavedModel for operations that could run malicious code when loaded. It works as a command-line tool and Python package. It is open source under Apache 2.0, in the Protect AI repositories on GitHub.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"safety","category_name":"Guardrails and security","page":"https://modelmoot.com/tools/modelscan","reviewed":"2026-11-15","checked":{"at":"2026-11-15T15:07:43.409Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}