Home / Skills / eval-leakage-audit
eval-leakage-audit
AlexZio00/sovereign-skillsSkill
Audits whether a verification (eval/metric/experiment/holdout) actually secures independent external ground truth, or whether the designer, the model, and the scorer are just confirming each other in a circle — via a 28-pattern taxonomy. Read-only. Use before trusting any 'how we'll know it worked' — A/B tests, holdouts, scores, validation — especially when a result feels too clean or self-confirming. 한국어: '이 검증 순환논리 아닌지 봐줘', '이 평가 편파적이야?', '이 벤치마크 셀프체크야?'.
Why this score
This repo hosts 10 skills, so its 141 stars are split between them (about 14 each) for scoring.
Popularity score: 56/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 20, 2026 at commit c06268371ab0, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This oneeval-leakage-audit AlexZio00/sovereign-skills · Skill | 56 | ★ 141 | ≈120 always | 26d ago |
| eval-audit ai-evals-course/evals-skills · Skill Same job: ai engineering | 66 | ★ 1.5k | ≈21 always | 1mo ago |
| eval-guide Calibre-Labs/reforge-ai-evals · Skill Same job: ai engineering | 54 | ★ 76 | ≈26 always | 16d ago |
| data-leakage-detection Tencent/AI-Infra-Guard · Skill Both about leakage | 78 | ★ 6.9k | ≈49 always | 16d ago |
| automationbench-eval bionic-gpt/bionic-gpt · Skill Same job: ai engineering | 73 | ★ 2.4k | ≈31 always | 28d ago |
| eval-design-forensics wanshuiyin/Anti-Autoresearch · Skill Same job: ai engineering | 60 | ★ 165 | ≈156 always | 18d ago |