Spatial Transcriptomics Mapper

Map spatial transcriptomics data from 10x Genomics Visium/Xenium onto.

This skill appears to be what it says: a local tool for mapping Visium/Xenium spatial transcriptomics data. Before installing/running: 1) Note the missing helper script referenced in SKILL.md (scripts/generate_test_data.py) — contact the author or remove the example invoking that script. 2) Inspect the full scripts/main.py locally (already included) for any additional behaviors you want to understand; the provided portion shows only local file I/O and plotting. 3) Run in an isolated environment (virtualenv or container) and install dependencies from PyPI to avoid polluting your system. 4) Provide only datasets you trust (the tool will read local HDF5/parquet/image files). 5) If you need network access restrictions, enforce them at the runtime/container level — the skill itself does not appear to perform network operations. 6) If you want higher assurance, run python -m py_compile scripts/main.py and a quick static scan for subprocess, socket, requests, urllib, or exec usage (none were detected in the inspected code).

Type: OpenClaw Skill Name: spatial-transcriptomics-mapper Version: 1.0.0 The skill bundle is a legitimate tool for spatial transcriptomics analysis, specifically designed for 10x Genomics Visium and Xenium data. The implementation in `scripts/main.py` uses standard scientific Python libraries (scanpy, squidpy, pandas, and matplotlib) to process genomic data and generate visualization reports. No evidence of data exfiltration, unauthorized network activity, or malicious execution was found; the file system access is limited to reading input data and writing results to a specified output directory. The `SKILL.md` instructions are well-structured for an AI agent and do not contain any prompt injection attempts or instructions to bypass security controls.