Geoskill: Geospatial Data Quality Audit

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

Overview

This is mostly a local geospatial audit tool, but it has review-worthy packaging and report-safety issues before use.

Install only in an isolated environment, audit trusted or sandboxed data packages first, and avoid opening generated HTML reports from untrusted inputs until report escaping is fixed. Expect local report files to be written or overwritten in the chosen output directory, and review the unresolved geoskill-data-fetcher dependency before relying on the tool.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• 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

Findings (19)

Dynamic attribute access via getattr()

Low

• Category: Dangerous Code Execution

Content

ds = netCDF4.Dataset(path, "r")
        result["dimensions"] = dict(ds.dimensions)
        result["variables"] = list(ds.variables.keys())
        result["global_attrs"] = {k: str(getattr(ds, k)) for k in ds.ncattrs()}
        ds.close()
    except ImportError:
        result["checks"].append({"id": "NETCDF4_MISSING", "severity": "warning",

• Confidence: 50% confidence
• Finding: result["global_attrs"] = {k: str(getattr(ds, k)) for k in ds.ncattrs()}

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence
• Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence
• Finding: This is mostly aligned with the declared geospatial QA purpose: the script scans local files, performs raster/vector/table/NetCDF checks, runs cross-file consistency checks, and writes JSON/HTML reports, issue GeoJSON, checksums, and machine-readable exit codes. However, the description says it checks raster, vector, table, NetCDF, and directory structure, while the code additionally exposes a synthetic data generation mode and recognizes LAS and document files. The LAS handling is especially incomplete: LAS files are detected but then effectively skipped as unknown in the audit workflow, so the top-level docstring overstates that part. The optional bbox/aoi interface is not used for downloading, only recorded in the manifest, so that is a minor extra behavior rather than a major concern. Overall, because the code includes capabilities not represented in the declared description, this should be flagged as a mismatch, though it remains closely related to the stated purpose.

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: The manifest describes a geospatial data quality audit skill that validates GIS data packages and produces reports, which implies local inspection of supplied datasets. The documented dependency on a shared data-download library for Planetary Computer, NASA POWER, and OSM introduces external data acquisition capability that is not justified by the stated QA-audit purpose.

Description-Behavior Mismatch

Medium

• Confidence: 91% confidence
• Finding: The requirements comment explicitly states use of a shared data-download library for external sources such as Planetary Computer, NASA POWER, and OSM. This behavior is absent from the manifest, which frames the skill as a unified data quality audit tool for provided GIS packages rather than a downloader or externally enriched validator.

Context-Inappropriate Capability

Medium

• Confidence: 93% confidence
• Finding: The manifest describes a geospatial data quality audit tool for checking supplied GIS data packages and generating QA outputs. This function creates new raster and GeoJSON content on disk as demo input, which is a content-generation capability not justified by the stated auditing purpose.

Intent-Code Divergence

Medium

• Confidence: 96% confidence
• Finding: The generated GeoJSON labels issues such as "Sample raster has no CRS metadata" and "Self-intersecting polygon detected," but the code writes a raster with CRS set to EPSG:4326 and creates simple box polygons that are valid. This is active intent/documentation divergence because the emitted issue metadata asserts defects that the generated geometries and raster do not actually contain.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The section header and prerequisite text switch to Chinese for critical setup guidance, including the 'must read' warning and prerequisite instructions. This imposes a language constraint on users without opt-in or justification, which matches the policy category for forced language or locale.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: This code creates an output directory and writes several files including JSON, HTML, GeoJSON, checksum, manifest, and QA summary artifacts. Although some paths are printed after writing, there is no prior confirmation prompt and the module/docstring does not clearly warn that running the tool will create or overwrite files in the target output location.

Natural-Language Policy Violations

Medium

• Confidence: 96% confidence
• Finding: The generated HTML explicitly sets lang="zh-CN", which forces a specific locale in the output regardless of the user's preferences or environment. This is a natural-language locale policy concern because the skill does not offer a language choice or document why a Chinese locale is required.

Scope Creep

Low

• Category: Excessive Agency

Content

copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,

• Confidence: 70% confidence
• Finding: NOT LIMITED TO

Unpinned Dependencies

Low

• Category: Supply Chain

Content

geoskill-data-fetcher>=0.2.0

# Third-party dependencies used by this skill
fiona
netCDF4
numpy
rasterio

• Confidence: 60% confidence
• Finding: fiona

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Third-party dependencies used by this skill
fiona
netCDF4
numpy
rasterio
shapely

• Confidence: 60% confidence
• Finding: netCDF4

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Third-party dependencies used by this skill
fiona
netCDF4
numpy
rasterio
shapely

• Confidence: 60% confidence
• Finding: numpy

Unpinned Dependencies

Low

• Category: Supply Chain

Content

fiona
netCDF4
numpy
rasterio
shapely

• Confidence: 60% confidence
• Finding: rasterio

Unpinned Dependencies

Low

• Category: Supply Chain

Content

netCDF4
numpy
rasterio
shapely

• Confidence: 60% confidence
• Finding: shapely

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Requirements for geospatial-data-quality-audit
# Shared data-download library (Planetary Computer / NASA POWER / OSM)
geoskill-data-fetcher>=0.2.0

# Third-party dependencies used by this skill
fiona

• Confidence: 50% confidence
• Finding: geoskill-data-fetcher>=0.2.0

Known Vulnerable Dependency: fiona — 2 advisory(ies): GHSA-g4m4-9q4c-mfw6 (Fiona affected by CVE-2020-14152 related to madler-zlib); GHSA-q5fm-55c2-v6j9 (Fiona affected by CVE-2023-45853 related to MiniZip madler-zlib)

Critical

• Category: Supply Chain
• Confidence: 90% confidence
• Finding: fiona

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: 90% confidence
• Finding: numpy

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.