Security audit

Geoskill: 屋顶光伏资源盘点

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent rooftop solar analysis tool with expected local outputs and disclosed optional data downloads, though users should note its manifests may record run parameters and dependencies are not pinned.

Install only in an environment where geospatial package resolution is acceptable, and review or pin dependencies for reproducible use. When using bbox/AOI auto-download mode, expect contacts to Microsoft Planetary Computer and NASA POWER and generated files under the output directory; avoid sharing output manifests if local paths or AOI details are sensitive.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (9)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill documentation describes writing multiple local output files and manifests, but there is no declared permissions model warning users that the skill performs file-write operations. Undeclared write capability can lead to unexpected filesystem changes, overwrite risks, and reduced user ability to make informed trust decisions before running the skill.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill states it will automatically download data from external services and write fetched metadata locally, but does not clearly and prominently disclose outbound network access and local file creation as side effects. This can surprise users, violate least astonishment, and create privacy, compliance, or supply-chain exposure if run in restricted environments.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The manifest stores raw CLI arguments via vars(args), which can unintentionally persist sensitive user-supplied values such as filesystem paths, AOI references, cache locations, or future authentication-related parameters. Because this data is written to output artifacts without warning or filtering, it can leak operational metadata when outputs are shared or published.

Unpinned Dependencies

Low

Category: Supply Chain
Content: geoskill-data-fetcher>=0.2.0 # Third-party dependencies used by this skill geopandas numpy rasterio scipy
Confidence: 98% confidence
Finding: geopandas

Unpinned Dependencies

Low

Category: Supply Chain
Content: # Third-party dependencies used by this skill geopandas numpy rasterio scipy shapely
Confidence: 98% confidence
Finding: numpy

Unpinned Dependencies

Low

Category: Supply Chain
Content: # Third-party dependencies used by this skill geopandas numpy rasterio scipy shapely
Confidence: 98% confidence
Finding: rasterio

Unpinned Dependencies

Low

Category: Supply Chain
Content: geopandas numpy rasterio scipy shapely
Confidence: 98% confidence
Finding: scipy

Unpinned Dependencies

Low

Category: Supply Chain
Content: numpy rasterio scipy shapely
Confidence: 98% confidence
Finding: shapely

Unpinned Dependencies

Low

Category: Supply Chain
Content: # Requirements for rooftop-solar-inventory # Shared data-download library (Planetary Computer / NASA POWER / OSM) geoskill-data-fetcher>=0.2.0 # Third-party dependencies used by this skill geopandas
Confidence: 99% confidence
Finding: geoskill-data-fetcher>=0.2.0

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.