Personal Genomics
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: personal-genomics Version: 4.2.0 The OpenClaw AgentSkills skill bundle 'personal-genomics' is classified as benign. The project explicitly prioritizes privacy, with all analysis running locally and no network requests made by the Python scripts or the interactive HTML dashboard. Code and documentation consistently reinforce this 'zero network requests' policy, and no evidence of data exfiltration, malicious execution, persistence, or unauthorized system access was found. Prompt injection attempts in `SKILL.md` are limited to instructing the agent on how to present results or activate the skill, aligning with its stated purpose rather than attempting to subvert agent behavior for harmful objectives.
Findings (0)
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.
Genetic reports can reveal sensitive health, ancestry, medication, and family-related information if they are shared, synced, indexed, or left unprotected.
The skill intentionally creates persistent local summaries and reports containing genetic and health information, including an AI-optimized summary that could be reused by an agent.
Output Location `~/dna-analysis/reports/` - `agent_summary.json` - AI-optimized, priority-sorted - `full_analysis.json` - Complete data - `report.txt` - Human-readable - `genetic_report.pdf` - Professional PDF report
Keep the output directory private, avoid adding these files to shared agent memory or cloud sync unless intended, and delete or encrypt reports when no longer needed.
If a user installs from the external repository rather than the packaged skill, they are trusting that repository and its dependencies.
The README documents an optional external GitHub clone and package-install path, while the registry metadata lists the source as unknown and provides no install spec.
git clone https://github.com/wkyleg/personal-genomics.git cd personal-genomics pip install -r requirements.txt
Prefer the packaged ClawHub install when available, and verify the external repository and requirements before running pip installs.
A user might make health or medication decisions based on generated genetic interpretations without professional review.
The skill generates medical-like recommendations related to medications and dosing. This is aligned with its stated pharmacogenomics purpose, but users could over-trust the output.
Medication Interaction Checker - cross-reference any medication list ... Dosing adjustments and alternative medication suggestions
Use the reports as educational input only and confirm medication, cancer-risk, carrier-status, or disease-risk findings with a qualified clinician or genetic counselor.
If this module is imported or run unintentionally, it may attempt to read a local `raw_data.txt` file from the current directory.
This file performs file loading at module top level using a hardcoded local filename, rather than only inside a guarded CLI entry point.
print("Loading raw data...")
df = pd.read_csv('raw_data.txt', sep='\t', comment='#',Use the documented main entry point with an explicit DNA file path, and avoid importing or running auxiliary scripts unless you intend their file access.