Send a request

ModelScan

by Protect AI (Palo Alto Networks)

Check model files before you load them

Scans model files (Pickle, H5, SavedModel) for embedded malicious code without loading the model. By Protect AI, now Palo Alto Networks.

Open SourceTrust 100Some practice neededRuns offlineTerminal · Python
Get it via OROBO

Checked sourcegithub.com/protectai/modelscanLicence: Apache-2.0checked 3 hours agoGitHub lists a SHA-256 checksum for every release file.

Have it set up for you instead:Request setup by OROBOOr start with the AI Compass: a written assessment at a fixed price of €490 (businesses only).

How it runs for you

Simulation starting …

Illustration, not a real test run

What you get

What you get

  1. 01Finds malicious code in Pickle, H5 and SavedModel files
  2. 02Scans without executing the model
  3. 03Free and open source (Apache 2.0)

For you if …

  • Anyone downloading models from Hugging Face
  • Teams with their own ML pipeline

Pick something else if …

  • If you only use ready-made cloud AI in an app

How to start

In three steps.

What you need
  • Python on your computer
  • The model file stored locally
  1. 1Install with pip install modelscan
  2. 2Run modelscan -p path/to/model
  3. 3Review findings and delete the file if in doubt

Safety check

7 of 7 checks passed

No known malicious patterns in the install instructionsactively maintainedLicence: Apache-2.0

Trust 100
Who is behind it?
  • Taken by OROBO from the official source. The maker has not joined OROBO yet.
Is the code clean?
  • Source code publicly visible
  • Licence: Apache-2.0
  • No known malicious patterns in the install instructions
Is it maintained?
  • Website reachable
  • Updated 38 days ago
Technical details & what we don’t check
  • Website loads fast
  • Website protection settings: 5 of 6 (website only, not the software)HSTS, CSP, nosniff, Frame-Schutz, Referrer-Policy

Claims about protection come from the maker. The trust score checks public signals, not effectiveness.

We automatically check origin, code patterns, licence, maintenance and reachability — again every day. We do not check whether the software fits your purpose, how it handles your data, or whether it works without errors. Last checked 3 hours ago. How OROBO checks

Alternatives for the same goal

Meta PurpleLlama (Llama Guard 4, Prompt Guard 2, LlamaFirewall)Make it safe · MetaFree guard models for your own AIOpen SourceTrust high, 100Runs offlinegarakMake it safe · NVIDIAHave your language model attacked on purposeOpen SourceTrust high, 100For developersGuardrails AIMake it safe · Guardrails AI (Harvey)Check AI answers before they move onOpen SourceTrust high, 100For developersNeMo GuardrailsMake it safe · NVIDIAFirm guardrails for your chatbotOpen SourceTrust high, 100For developersGiskardMake it safe · GiskardScan LLM apps for hallucinations and leaksOpen SourceTrust high, 100For developersPyRITMake it safe · Microsoft (AI Red Team)Automate red teaming for generative AIOpen SourceTrust high, 100For developersSnyk Agent Scan (formerly Invariant MCP-Scan)Make it safe · Snyk (ex-Invariant Labs team)Scan installed MCP servers and skills for trapsOpen SourceTrust high, 100For developersCisco Skill ScannerMake it safe · Cisco AI DefenseCheck agent skills before you install themOpen SourceTrust high, 100For developers

Facts

AreaMake it safe
PriceOpen Source
LicenceApache-2.0
Runs onTerminal, Python
Popular with developers★ 793 GitHub
Last updated28 Sept 2026
Sourceprotectai/modelscan ↗
I am the maker