地动仪气候模型 Dizhenyi Climate Model
PassAudited by ClawScan on May 5, 2026.
Overview
This appears to be a climate-modeling skill with local Python scripts; no evidence of credential access, exfiltration, persistence, or destructive behavior was found.
This skill looks safe to install for local climate-model experiments. Before running it, be aware that it asks you to install numpy and execute local Python scripts; use a virtual environment and avoid running as an administrator/root user.
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.
Installing dependencies could pull a different or compromised package version if the package source or environment is not trusted.
The dependency is unpinned. This is normal for a numpy-based climate calculation skill, but users rely on the package source and currently get whatever numpy version pip resolves.
numpy
Install in a virtual environment, use a trusted package index, and consider pinning numpy to a known-good version.
Using the skill means running local code on the user's machine and producing local output files.
The skill is designed to run included local Python scripts. This is expected for the stated modeling purpose, and the visible code is numerical/printing logic rather than network, credential, or destructive behavior.
python3 scripts/climate_predictor.py long
Review the scripts if desired and run them in a normal user account or virtual environment rather than a privileged shell.