Equity Scorer
PassAudited by ClawScan on May 1, 2026.
Overview
The skill appears to be a coherent local genomics analysis tool, with only normal cautions about sensitive genomic outputs and third-party Python dependencies.
Before installing, be aware that this skill is designed to read local genomic or ancestry datasets and write analysis outputs. Use it in an isolated Python environment, keep input and output files in a secure location, and review generated reports before sharing them.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Future installs may resolve to newer dependency versions with different behavior or vulnerabilities.
The skill installs third-party Python packages without pinned versions. These are expected scientific dependencies for the stated purpose, but unpinned dependencies can change over time.
uv | package: biopython; pandas; scikit-learn; matplotlib; numpy
Install in an isolated environment and prefer pinned dependency versions or a lockfile when reproducibility is important.
Generated reports could reveal sensitive information about sample ancestry composition or genomic datasets if shared or stored insecurely.
The skill processes genomic/ancestry data and persists derived reports, tables, figures, and checksums locally. This is purpose-aligned, but the resulting files may contain sensitive cohort summaries or identifying metadata.
Compute HEIM diversity and equity metrics from VCF or ancestry data... equity_report/ report.md ... tables/ ... checksums.sha256
Use a controlled output directory, avoid sharing reports without review, and remove outputs when they are no longer needed.