Geoskill: Crop Type Mapping

• Outcome: Review
• Latest audit: Jul 31, 2026 · 11:34 AM UTC
• Version: 2.0.0

Overview

The skill is packaged as real crop mapping from satellite imagery, but the inspected code mainly generates synthetic scenes and can report demo accuracy, so users could mistake simulated results for operational analysis.

Review this as a prototype or demo skill, not an operational crop-mapping tool. Before using it for planning, insurance, government, or other high-impact decisions, require real imagery ingestion, explicit data provenance, SAR support removal or implementation, clear demo-only labeling when synthetic data is used, and pinned dependencies.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (11)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 90% confidence
• Finding: A significant description-behavior mismatch is a real security and trust issue because users may supply sensitive AOIs, labels, or operational workflows under the assumption that the skill processes real optical/SAR data as advertised, while it may instead fabricate synthetic inputs, omit SAR processing, or self-score against generated truth. This can mislead downstream decisions, hide nontransparent processing, and undermine assurance for government, insurance, or agricultural intelligence use cases.

Description-Behavior Mismatch

High

• Confidence: 98% confidence
• Finding: The skill is presented as performing crop mapping from optical/SAR imagery, but the implementation generates synthetic NDVI scenes and then reports results and manifests as if they were derived from actual analysis. In an agricultural intelligence context, this can mislead downstream users into making operational or policy decisions based on fabricated outputs, which is a security-relevant integrity failure.

Description-Behavior Mismatch

Medium

• Confidence: 95% confidence
• Finding: The skill description and manifest imply SAR support, but the code only models optical-style NDVI/reflectance features and does not ingest or process SAR data. This creates a false capability claim that can cause users to trust classifications in conditions where SAR is specifically needed, such as cloud-obscured monitoring.

Intent-Code Divergence

Medium

• Confidence: 92% confidence
• Finding: The inline comment suggests production behavior such as STAC search, download, and preprocessing, but the code path only generates synthetic data. This kind of misleading implementation note increases the risk that reviewers, operators, or integrated agents will assume real remote-sensing processing is happening when it is not.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

geoskill-data-fetcher>=0.2.0

# Third-party dependencies used by this skill
fiona
numpy
rasterio
scikit-learn

• Confidence: 94% confidence
• Finding: fiona

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Third-party dependencies used by this skill
fiona
numpy
rasterio
scikit-learn
scipy

• Confidence: 94% confidence
• Finding: numpy

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Third-party dependencies used by this skill
fiona
numpy
rasterio
scikit-learn
scipy
shapely

• Confidence: 94% confidence
• Finding: rasterio

Unpinned Dependencies

Low

• Category: Supply Chain

Content

fiona
numpy
rasterio
scikit-learn
scipy
shapely

• Confidence: 95% confidence
• Finding: scikit-learn

Unpinned Dependencies

Low

• Category: Supply Chain

Content

numpy
rasterio
scikit-learn
scipy
shapely

• Confidence: 93% confidence
• Finding: scipy

Unpinned Dependencies

Low

• Category: Supply Chain

Content

rasterio
scikit-learn
scipy
shapely

• Confidence: 93% confidence
• Finding: shapely

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Requirements for crop-type-mapping
# Shared data-download library (Planetary Computer / NASA POWER / OSM)
geoskill-data-fetcher>=0.2.0

# Third-party dependencies used by this skill
fiona

• Confidence: 95% confidence
• Finding: geoskill-data-fetcher>=0.2.0

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.