Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
**v1.1.0 summary:** Adds reasoning trace correlation detection to validator correlation analysis. - Introduces evaluation trace correlation: detects correlated validators by analyzing reasoning patterns, even when training provenance is undisclosed. - Updated analyzer to include six dimensions of correlation, adding trace-based analysis to existing provenance, model, behavioral, and evasion checks. - Documentation expanded to describe evaluation trace correlation, its use, outputs, and how it enables correlation detection without self-report. - Updated agent capabilities metadata to reflect the new evaluation-trace-correlation-analysis feature. - Keeps previous behavioral and provenance correlation checks, now enhanced by trace-based detection.
What This Skill Does
Analyzes groups of attestation validators to detect epistemic correlation caused by shared training data, base models, or fine-tuning pipelines. Organizationally independent validators that share upstream dependencies produce the same blind spots, making multi-validator attestation no stronger than a single check. v1.1 adds evaluation trace correlation analysis to detect shared reasoning patterns when validators do not disclose their training provenance.
Standard attestation root analysis checks organizational independence but cannot detect epistemic correlation from shared training lineage, so correlated validators pass conventional audits while remaining vulnerable to the same evasion technique.
When to use it
- Checking if three validators in a deployment actually provide independent coverage
- Detecting when two validators from different orgs share a base model or training dataset
- Testing evasion transferability across a validator pool before a security audit
- Inferring provenance correlation from published evaluation traces without provenance disclosure
- Calculating effective independent validator count in an attestation chain
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Analyze validator correlation for Validator-A, Validator-B, Validator-C attesting data-processor skill
- 1Collect training provenance disclosures for each validator, noting base model and fine-tuning dataset
- 2Run behavioral correlation test on 50 edge-case skills, computing pairwise agreement rates against the independence baseline
- 3Calculate evasion transferability by testing whether skills evading Validator-A also evade Validator-B and Validator-C
- 4Compare reasoning path structure across validator pairs if evaluation traces are published
- 5Produce effective independent validator count and assign correlation verdict: INDEPENDENT, WEAKLY-CORRELATED, CORRELATED, or MONOCULTURE
Validator-A and Validator-B share base model (GPT-class) and fine-tuning dataset (SecDataset-v2); A-B agreement rate 94% vs 70% independence baseline; evasion transferability A to B 87.5%; effective independent validator count 2.1; verdict CORRELATED