Implement Dropbox's repeated token attack as a probe in garak. Check out their documentation and code at https://github.com/dropbox/llm-security!

Take a look in garak/garak/probes/ to see how probes work, before giving this a go. Try to write as few methods as possible. When you're done, add a test in garak/tests/probes/ that checks things are working as expected. If you need help, you can comment here, or find us in discord!

A guide to testing for contributing is at https://reference.garak.ai/en/latest/contributing.html

For a reference guide to how probes work, see https://reference.garak.ai/en/latest/garak.probes.base.html