Shadow AI Scanner: figures & benchmarks
Evidence for Shadow AI Scanner: 1. Evidence pack · 2. Answers to buyer questions · 3. Figures & benchmarks · 4. Selling tools · IHVRK kit · Learn it · why these pages exist
Every number on this page is read from the signed transcript inside the IHVRK kit; none is typed in by hand.
4/4
claims matched when recorded
3
attack cases refused or flagged as claimed
137 ms
median round trip (min 128, max 228), incl. network
| # | Kind | Claim | Recorded value | HTTP | ms |
|---|---|---|---|---|---|
| C01 | control | Ordinary web app calling GitHub -> No AI used: score 0, no false alarm. | 0 | 200 | 228 |
| C02 | attack | Gemini called over plain HTTP, plus AWS Bedrock -> Raw web calls to AI services are found, not only library imports. | 10 | 200 | 137 |
| C03 | attack | The OpenAI library -> AI library import found. | 2 | 200 | 129 |
| C04 | attack | The Anthropic library -> AI library import found. | 2 | 200 | 128 |
Copy the table (paste into a spreadsheet)
id kind claim recorded_value expected http ms recorded_at C01 control Ordinary web app calling GitHub -> No AI used: score 0, no false alarm. 0 [0] 200 228 2026-11-03T22:54:48+00:00 C02 attack Gemini called over plain HTTP, plus AWS Bedrock -> Raw web calls to AI services are found, not only library imports. 10 [10] 200 137 2026-11-03T22:54:49+00:00 C03 attack The OpenAI library -> AI library import found. 2 [2] 200 129 2026-11-03T22:54:50+00:00 C04 attack The Anthropic library -> AI library import found. 2 [2] 200 128 2026-11-03T22:54:50+00:00
Download: figures.tsv · transcript.json (full answers) · whole kit
How to read these numbers
- Recorded 2026-11-03T22:54:51+00:00 against cainstudio.online from our build host; times include the internet round trip.
- They show these inputs, not every possible input. Known misses are on the limits page.
- This is not a load test, an SLA or a third-party benchmark. Re-run it yourself:
python3 verify.py --live.