CAIN-42 CLAWXVibeGuard: figures & benchmarks
Evidence for VibeGuard: 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.
6/6
claims matched when recorded
4
attack cases refused or flagged as claimed
42 ms
median round trip (min 34, max 49), incl. network
| # | Kind | Claim | Recorded value | HTTP | ms |
|---|---|---|---|---|---|
| C01 | attack | Sample: Slingshot Hallucinated Package (Cursor / Windsurf AI diff) -> AI-written Python checked by syntax tree and the supply-chain guard. | "POISONED_DIFF" | 200 | 49 |
| C02 | attack | Sample: Fabricated Confidence Metric (Mock-dressed-as-computation) -> AI-written Python checked by syntax tree and the supply-chain guard. | "UNSAFE_DIFF" | 200 | 40 |
| C03 | control | Sample: Clean Standard-Library HMAC Token Verifier -> AI-written Python checked by syntax tree and the supply-chain guard. | "CLEAN" | 200 | 39 |
| C04 | attack | Your code: random number as a risk score -> A fake measurement looks like a real one. | "UNSAFE_DIFF" | 200 | 34 |
| C05 | attack | Your code: swallowed error in auth -> Errors hidden with pass. | "UNSAFE_DIFF" | 200 | 42 |
| C06 | control | Your code: plain arithmetic -> Ordinary code passes. | "CLEAN" | 200 | 43 |
Copy the table (paste into a spreadsheet)
id kind claim recorded_value expected http ms recorded_at C01 attack Sample: Slingshot Hallucinated Package (Cursor / Windsurf AI diff) -> AI-written Python checked by syntax tree and the supply-chain guard. "POISONED_DIFF" ["POISONED_DIFF", "UNSAFE_DIFF"] 200 49 2026-11-03T22:47:42+00:00 C02 attack Sample: Fabricated Confidence Metric (Mock-dressed-as-computation) -> AI-written Python checked by syntax tree and the supply-chain guard. "UNSAFE_DIFF" ["POISONED_DIFF", "UNSAFE_DIFF"] 200 40 2026-11-03T22:47:43+00:00 C03 control Sample: Clean Standard-Library HMAC Token Verifier -> AI-written Python checked by syntax tree and the supply-chain guard. "CLEAN" ["CLEAN"] 200 39 2026-11-03T22:47:43+00:00 C04 attack Your code: random number as a risk score -> A fake measurement looks like a real one. "UNSAFE_DIFF" ["UNSAFE_DIFF", "POISONED_DIFF"] 200 34 2026-11-03T22:47:44+00:00 C05 attack Your code: swallowed error in auth -> Errors hidden with pass. "UNSAFE_DIFF" ["UNSAFE_DIFF", "POISONED_DIFF"] 200 42 2026-11-03T22:47:44+00:00 C06 control Your code: plain arithmetic -> Ordinary code passes. "CLEAN" ["CLEAN"] 200 43 2026-11-03T22:47:45+00:00
Download: figures.tsv · transcript.json (full answers) · whole kit
How to read these numbers
- Recorded 2026-11-03T22:47:45+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.