Geoskill: Aquaculture Pond Mapping

• Outcome: Review
• Latest audit: Jul 31, 2026 · 11:24 AM UTC
• Version: 2.0.0

Overview

The skill is not clearly malicious, but it can download satellite data and then produce synthetic or incomplete pond-mapping outputs that users could mistake for real analysis.

Install only after reviewing the code path for your intended workflow. Require a real --input-ndwi dataset or a fixed, verified download-to-analysis flow before relying on outputs, and treat default no-input results as demo/synthetic. Pin dependencies or use a reviewed lockfile before installing in a sensitive environment.

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: 84% confidence
• Finding: The skill description focuses on pond mapping, but the documentation also states it can automatically download remote data when given a bbox and date range. Undeclared network access expands the trust boundary, can surprise users in restricted environments, and may result in unintended external requests, data egress, or operational policy violations.

Description-Behavior Mismatch

Medium

• Confidence: 94% confidence
• Finding: The script silently falls back to synthetic data when no input raster is provided, yet still produces realistic-looking outputs and manifests. In an automated agent workflow, this can mislead users or downstream systems into treating fabricated analysis as real remote-sensing results, causing integrity and decision-making failures.

Description-Behavior Mismatch

Medium

• Confidence: 89% confidence
• Finding: The module description claims wetland/cropland conversion analysis, but the implementation never performs that analysis. This is a capability-integrity issue: users may rely on absent environmental impact outputs, leading to false assurance and incorrect operational or policy decisions.

Description-Behavior Mismatch

Medium

• Confidence: 87% confidence
• Finding: The advertised skill is multi-temporal, but auto-download retrieves only one Sentinel-2 item and a narrow asset subset, which does not support the claimed temporal monitoring workflow. This mismatch can produce outputs that appear to represent temporal analysis without sufficient source data, undermining result integrity.

Missing User Warnings

Medium

• Confidence: 81% confidence
• Finding: The skill can automatically download remote data and write numerous output files without an explicit upfront warning or confirmation. In agent contexts, hidden network and filesystem side effects can violate user expectations, create unwanted data persistence, and increase operational risk even if the behavior is not overtly malicious.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

geoskill-data-fetcher>=0.2.0

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

• Confidence: 92% confidence
• Finding: numpy

Unpinned Dependencies

Low

• Category: Supply Chain

Content

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

• Confidence: 92% confidence
• Finding: rasterio

Unpinned Dependencies

Low

• Category: Supply Chain

Content

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

• Confidence: 92% confidence
• Finding: scipy

Unpinned Dependencies

Low

• Category: Supply Chain

Content

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

# Third-party dependencies used by this skill
numpy

• Confidence: 95% 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: 71% confidence
• Finding: numpy

Known Vulnerable Dependency: scipy — 4 advisory(ies): CVE-2013-4251 (SciPy creates insecure temporary directories); CVE-2013-4251 (The scipy.weave component in SciPy before 0.12.1 creates insecure temporary dire); CVE-2023-25399 (A refcounting issue which leads to potential memory leak was discovered in scipy) +1 more

High

• Category: Supply Chain
• Confidence: 78% confidence
• Finding: scipy

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.