Geoskill: Wetland Change Monitor

• Outcome: Pass
• Latest audit: Jul 31, 2026 · 1:43 PM UTC
• Version: 3.0.0

Overview

This wetland analysis skill is purpose-aligned and disclosed, with ordinary file outputs and optional data downloads that users should scope carefully.

Install only in an environment where network access to remote geospatial data sources and writing analysis outputs are acceptable. Use an explicit --output-dir, preferably a fresh directory, and consider pinning or reviewing dependencies before production use.

SkillSpector

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
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 92% confidence
• Finding: The skill documentation indicates it writes output files such as GeoTIFFs, GeoJSON, CSV, and JSON manifests, yet no permissions are declared. Undeclared file-write capability weakens the trust boundary for users and orchestration systems, because the skill can modify the filesystem without an explicit, reviewable permission contract.

Missing User Warnings

Medium

• Confidence: 79% confidence
• Finding: The workflow performs automatic network access and downloads remote assets based on user-supplied AOI/date inputs, then writes them to disk, without an explicit opt-in or clear warning. In an agent or automation context, this can cause unintended external requests, unanticipated storage consumption, and side effects that violate least surprise or environment policies.

Missing User Warnings

Low

• Confidence: 71% confidence
• Finding: The script creates an output directory and writes multiple files automatically, potentially overwriting prior results in predictable locations, without an explicit upfront notice or safe-write controls. While this is not severe in isolation, in agent-driven execution it can lead to unintended filesystem modification, confusion, or loss of previous outputs.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

geoskill-data-fetcher>=0.2.0

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

• Confidence: 91% confidence
• Finding: The dependency is unpinned, so builds may resolve to different NumPy versions over time, reducing reproducibility and increasing supply-chain risk if a bad or incompatible release is pulled. In this skill, NumPy is a core scientific package rather than an inherently dangerous component, so the issue is primarily dependency hygiene rather than immediate exploitability.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

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

• Confidence: 91% confidence
• Finding: Rasterio is specified without a version pin, which allows uncontrolled version drift and can introduce breaking changes or newly introduced vulnerable releases during installation. Given this skill processes geospatial raster data, dependency integrity matters, but the risk here remains a low-severity supply-chain and reproducibility concern.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

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

• Confidence: 91% confidence
• Finding: SciPy is unpinned, which makes environments non-reproducible and may expose the skill to vulnerable or incompatible future releases. In this scientific-analysis context, the package choice is normal and likely benign, but leaving it floating is still a genuine supply-chain weakness.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

numpy
rasterio
scipy
shapely

• Confidence: 90% confidence
• Finding: Shapely is also unpinned, creating the same class of risk: dependency drift, accidental installation of problematic versions, and reduced reproducibility. The skill's wetland-monitoring purpose does not make this dependency unusually dangerous, but it is still a valid low-severity security finding.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Requirements for wetland-change-monitor
# Shared data-download library (Planetary Computer / NASA POWER / OSM)
geoskill-data-fetcher>=0.2.0

# Third-party dependencies used by this skill
numpy

• Confidence: 94% confidence
• Finding: The shared library is only lower-bounded (>=0.2.0), so any newer release may be installed, including one with breaking behavior or a compromised supply-chain event. Because this package appears to handle external data acquisition from remote services, version drift here is somewhat more sensitive than the pure scientific libraries listed below.

Static analysis

No suspicious patterns detected.