Add Garak (NVIDIA LLM vulnerability scanner) parser

[Dashtid]

Description

Adds a parser for garak, NVIDIA's LLM vulnerability scanner, implementing the request in #14878 (and aligned with the AI-testing direction in discussion #13242).

The parser ingests garak's JSON Lines hit log (garak.<run_id>.hitlog.jsonl). Every line in a hit log is a detector hit, so each record becomes a Finding; hits for the same probe/target/detector are aggregated into one Finding (nb_occurences, keeping the most severe rung seen).

• Severity is derived from the detector score (0–1) and adjusted by probe family — active-attack/jailbreak families (e.g. promptinject, dan, malwaregen, xss) nudge up; content/quality families (e.g. continuation, misleading) nudge down. Note: many garak detectors emit a binary 1.0, so in practice the probe-family adjustment does most of the differentiating. Happy to tune this to maintainer preference.
• CWE is mapped from the probe family as a deliberately coarse starter, verified against MITRE: prompt-injection → CWE-1427, XSS → CWE-79, info-leak → CWE-200, default → CWE-1426 (Improper Validation of Generative AI Output).
• Prompt/output text is extracted from garak's nested Conversation/Message structures (per garak/evaluators/base.py), with fallbacks for plain-string payloads.
• Registered for hash_code deduplication on title + severity + component_name. description is intentionally excluded because garak samples the prompt/output non-deterministically per run, so including it would prevent the same weakness from deduplicating across repeated scans.

Test results

Adds unittests/tools/test_garak_parser.py covering: zero/one/many findings, the full score→severity matrix, the CWE mapping, aggregation severity-escalation (and that a later lower-scored hit does not downgrade), nested prompt/output extraction, bytes + UTF-8 BOM + non-ASCII input, and rejection of non-JSONL input. Sample hit logs are under unittests/scans/garak/.

Marked as a draft so CI can validate the full DojoTestCase suite before review.

Documentation

Adds docs/content/supported_tools/parsers/file/garak.md.

Checklist

• Submitted against dev
• Ruff-compliant (ruff.toml)
• Python 3.13 compliant
• Documentation included
• No model changes (no migration needed)
• Unit tests added
• Labels (for maintainers): suggest Import Scans and settings_changes (touches settings.dist.py for deduplication)

Closes #14878

[Dashtid]

This implements the garak parser requested in #14878. @mcdonaid1379 — you'd mentioned wanting to take it on; I had a working implementation ready, so opened this. Happy to coordinate if you'd already started, and of course defer to the maintainers on direction.

A note for reviewers: I couldn't run the full DojoTestCase suite locally (a network issue pulling the test-DB image), so the unit tests here are pending the first-time-contributor CI approval — keen to see them run and will fix anything that surfaces.

[valentijnscholten]

Does this mean the severity could change over time when it finds more or less occurences in certain "probe". If yes, this could affect deduplication in its current config. Do we really need severity in the hash code config? It rarely is useful and rarely stable enough to be reliable.