Interactive scorecard
AI-Sec Tool Scorecard Builder
Pick 1-3 reviewed tools, then tune what matters for your context. Every dimension score comes from the documented review on this site, which is built from vendor documentation, source code and published evaluations, and the evidence sentence behind each score names its source inline. Where a figure is vendor-stated it is labelled as such, and where nobody publishes a figure the evidence says so instead of inventing one.
Each dimension is scored 0-5 from the linked review, on published evidence rather than first-hand testing. 5 = strongest documented; 0 = effectively absent or a hard weakness. Higher is always better, including for cost/effort dimensions (5 = lowest cost / least effort). A dimension with no published evidence in either direction sits mid-scale and says so. Scores reviewed 2026-09.
All tools & raw review scores
| Tool | Detection rate | Novel-attack resilience | Low false-positive cost | Latency fit | Integration effort | Deployment flexibility | Maintenance signal |
|---|---|---|---|---|---|---|---|
| Garak Apache 2.0 (open source) | 4 | 2 | 3 | 1 | 2 | 4 | 4 |
| Lakera Guard Commercial (SaaS; enterprise self-host) | 4 | 3 | 3 | 3 | 5 | 4 | 4 |
| Guardrails AI Apache 2.0 (open source) | 3 | 2 | 3 | 3 | 4 | 5 | 4 |
| PyRIT MIT (open source) | 4 | 3 | 3 | 3 | 4 | 4 | 5 |
| Rebuff Apache 2.0 (open source) | 3 | 2 | 3 | 3 | 2 | 5 | 1 |
| Arize Phoenix Elastic License 2.0 (source-available) | 3 | 2 | 2 | 2 | 4 | 5 | 4 |
More single-product reviews
Reviewed on the same evidence basis, but not part of the interactive matrix above.