Geoskill: Agricultural Disaster Assessment

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

Overview

This skill performs a disclosed agricultural raster analysis workflow with expected output files and optional geospatial data download, but users should note the external fetch mode and unpinned dependencies.

Before installing, confirm you are comfortable with optional external geospatial data requests when using bbox/AOI date-range mode, choose an output/cache directory you control, and prefer a pinned dependency lockfile for reproducible installs.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (9)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 83% confidence
• Finding: The skill documentation describes writing multiple outputs to disk, but the skill metadata does not declare any permissions for file writing. Undeclared write capability weakens user consent and sandbox/policy enforcement because operators may assume the skill is read-only when it is not.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 92% confidence
• Finding: The documented purpose is local raster fusion for disaster assessment, but the behavior expands to remote data download, synthetic data generation, and additional report/manifests. This mismatch is dangerous because users and enforcement systems may authorize the skill for a narrower purpose while it performs broader network and file operations than expected.

Description-Behavior Mismatch

Medium

• Confidence: 88% confidence
• Finding: The documentation expands the skill from local processing into automatic remote download from Microsoft Planetary Computer. Even if the source is legitimate, automatic external retrieval changes the trust boundary, introduces network dependence, and can cause unintended data transfer or execution in restricted environments.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The markdown describes automatic remote data download without warning about network activity or external data transfer. This is risky because users may provide AOIs, date ranges, or paths without realizing the skill will contact an outside service, which can violate privacy, policy, or air-gapped environment expectations.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

geoskill-data-fetcher>=0.2.0

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

• Confidence: 96% 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 agricultural-disaster-assessment
# 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: 87% confidence
• Finding: numpy

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.