Garakgarak 0.17.0 Ā· Python 3.10+
0%
1
Curious builder0 XP earned Ā· 300 to level 2
0 daysFinish a lesson to begin
Badge collection0 of 6 unlocked
23 small wins to finish your pathNext lesson →

What garak also does

This course taught the scanning loop and the parts of it an application needs. Garak is larger, and knowing the shape of the rest is worth ten minutes.

Not covered hereWhat it is
About 190 probesThis course ran a handful. The rest are the catalogue you are paying for
About 117 detectorsIncluding several that run their own models
The report HTMLA scored summary written beside the JSON, grouped by risk
Tiers and the z-scoreGarak's own scoring of how much a result matters
The intent serviceThe risk categories in the banner, and how results roll up to them
Harnessesprobewise and pxd, which decide how probes and detectors are paired
Around 44 generatorsEvery model API, plus rest, and a browser
PayloadsReusable content that several probes draw from
--parallel_attemptsConcurrency, which the run suggests when your target supports it

Where it sits beside the other tools

PyRIT is the other red teaming course here. Garak is a scanner: a catalogue of known weaknesses, run in bulk, reported as rates. PyRIT is a harness: you build the attack, control the conversation, and keep everything in a database. Garak answers does my system have any of these known problems; PyRIT answers what happens if I try this.

Guardrails AI and NeMo Guardrails are the fix rather than the finding. A scan tells you an answer got through; a guardrail is what stops it next time. Running a scan against a system with rails, and again with them off, is how you show a rail is worth its latency.

A scan is a finding, not a fix. The value arrives when a hit becomes a rail, or a test, or a line in your own report reader. A scan you ran once and read once has told you nothing you kept.
Try it yourself
  • Open the HTML report from any lesson and find the risk grouping.
  • Read the probe list and pick five you would run against your own system.
  • Take one hit from a scan and write the rail that would stop it.

Little by little, you're building something great.