Geoskill: 尾矿库风险评估

• Outcome: Pass
• Latest audit: Jul 30, 2026 · 3:48 PM UTC
• Version: 1.0.0

Overview

This skill is a disclosed geospatial risk-screening tool; its network downloads and file outputs fit its stated purpose, with dependency and location-privacy cautions.

Before installing, treat bbox or AOI use as network-enabled: it can send the area of interest and date range to external geospatial data services and store downloaded data locally. Use local DEM and water-mask files instead for sensitive sites, and consider pinning or locking dependencies in controlled environments.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Context-Inappropriate Capability

Medium

• Confidence: 90% confidence
• Finding: This function introduces automatic external network retrieval of DEM and Sentinel-2 data based on user-provided AOI/bbox inputs. In agent or sandboxed environments, undeclared outbound network access can violate trust boundaries, leak sensitive geographic targets through requests, and cause the skill to perform actions beyond a user's expectation.

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: The main analysis path automatically triggers remote data acquisition whenever bbox or AOI inputs are present and local DEM/water-mask inputs are absent. Because this happens in normal execution flow without a dedicated consent gate, a caller may unknowingly cause network egress and disclose sensitive site locations or operational interest in specific tailings facilities.

Missing User Warnings

Low

• Confidence: 93% confidence
• Finding: The code performs automatic downloads with only minimal status output after the fact and no clear user-facing warning before external access occurs. In a security-sensitive workflow, lack of transparency around network activity increases the risk of unintentional data disclosure and policy noncompliance, especially given the sensitive nature of mining infrastructure locations.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

geoskill-data-fetcher>=0.2.0

# Third-party dependencies used by this skill
numpy
rasterio
shapely

• Confidence: 95% confidence
• Finding: numpy

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Third-party dependencies used by this skill
numpy
rasterio
shapely

• Confidence: 95% confidence
• Finding: rasterio

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Third-party dependencies used by this skill
numpy
rasterio
shapely

• Confidence: 95% confidence
• Finding: shapely

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Requirements for tailings-dam-risk
# Shared data-download library (Planetary Computer / NASA POWER / OSM)
geoskill-data-fetcher>=0.2.0

# Third-party dependencies used by this skill
numpy

• Confidence: 98% confidence
• Finding: geoskill-data-fetcher>=0.2.0

Known Vulnerable Dependency: numpy — 10 advisory(ies): CVE-2014-1859 (Numpy arbitrary file write via symlink attack); CVE-2021-41495 (NumPy NULL Pointer Dereference); CVE-2021-33430 (NumPy Buffer Overflow (Disputed)) +7 more

Critical

• Category: Supply Chain
• Confidence: 86% confidence
• Finding: numpy

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.