Geoskill: Renewable Energy Site Selection

• Outcome: Review
• Latest audit: Jul 31, 2026 · 12:09 PM UTC
• Version: 2.0.0

Overview

This skill is a disclosed renewable-energy GIS analysis tool with network data download and file-output behavior that users should understand before running.

Install only if you are comfortable with a GIS skill that writes analysis outputs and may contact NASA POWER and Planetary Computer when bbox/AOI and date-range inputs are used. Prefer running it in a project-specific directory, set an explicit output/cache directory, and review or pin dependencies for reproducible installs.

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• 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)

eval() call detected

High

• Category: Dangerous Code Execution

Content

Returns exit code (0 = ok, 2 = arg error)."""
    # File existence
    for flag, accessor in FILE_ARGS.items():
        path = eval(accessor)
        if path is None or path == "":
            continue
        if not Path(str(path)).exists():

• Confidence: 98% confidence
• Finding: The use of eval() to resolve argument access is unnecessary and dangerous because it executes Python expressions at runtime. Today the accessor strings come from a constant dictionary, but this pattern creates a latent code-execution sink that becomes exploitable if the mapping is ever influenced by untrusted input or modified during maintenance; in a CLI/data-processing skill that may be run in automated environments, arbitrary code execution would have severe consequences.

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 74% confidence
• Finding: The skill advertises output generation and file-writing behavior but declares no permissions, creating a transparency and policy-enforcement gap. In agent environments, undeclared write capability can lead to unexpected filesystem modifications, overwriting files, or writing artifacts into sensitive locations if downstream code is not constrained.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 88% confidence
• Finding: The documented purpose describes a local GIS suitability analysis tool, but the behavior expands to remote data retrieval, DEM searching/downloading, synthetic data generation, and additional reporting outputs. This mismatch is dangerous because users and orchestrators may authorize the skill under a narrower trust model while it performs networked and broader side-effecting actions that increase attack surface, data exposure, and operational risk.

Description-Behavior Mismatch

Medium

• Confidence: 83% confidence
• Finding: The skill explicitly advertises automatic downloading of external data from NASA POWER when only a bounding box and date range are supplied. Automatic network retrieval introduces supply-chain, privacy, and reproducibility risks, especially if users do not expect external requests or if the fetched content is later trusted for processing without strong validation.

Intent-Code Divergence

Medium

• Confidence: 80% confidence
• Finding: The later documentation section introduces alternate inputs and an automatic download workflow that contradict the earlier CLI contract based on local raster inputs. Contract inconsistencies are dangerous because they defeat policy review and user expectations, making it easier for hidden network or file-processing behavior to slip through approval and increasing the chance of insecure invocation paths.

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: The dependency is unpinned, so installs may resolve to different versions over time, reducing build reproducibility and increasing supply-chain risk if a bad or incompatible release is published. In a geospatial analysis skill, this can affect integrity and stability, though by itself it is not evidence of active compromise.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

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

• Confidence: 95% confidence
• Finding: The rasterio dependency is unpinned, which allows future installations to pull newer versions without review. That creates reproducibility and supply-chain exposure, especially for packages with native/GDAL-linked components that can introduce breaking changes or security issues.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

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

• Confidence: 95% confidence
• Finding: Shapely is declared without a fixed version, so dependency resolution is non-deterministic and could silently introduce vulnerable or incompatible releases. In this site-selection skill, that most directly threatens reliability and supply-chain hygiene rather than causing immediate direct exploitation.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Requirements for renewable-energy-site-selection
# 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: The custom/shared package geoskill-data-fetcher is only lower-bounded (>=0.2.0), so any later release may be installed automatically. Because it appears to handle external data downloads, an unexpected update in this package could materially affect network-facing behavior and increases supply-chain risk beyond a typical utility library.

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical

• Code: suspicious.dynamic_code_execution
• Location: scripts/renewable_energy_site_selection.py:94