Geoskill: Land Subsidence InSAR

• Outcome: Review
• Latest audit: Jul 31, 2026 · 12:13 PM UTC
• Version: 2.0.0

Overview

The skill is not malicious, but it can produce land-subsidence reports from data that is not actually displacement data, which could mislead users making hazard decisions.

Install only if you understand that bbox/AOI auto-download mode is not a reliable InSAR displacement workflow. For real subsidence assessment, use vetted displacement rasters, avoid relying on the GRD auto-download output for decisions, and pin/review dependencies before use in controlled environments.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (6)

Intent-Code Divergence

Medium

• Confidence: 96% confidence
• Finding: The auto-download path claims to support InSAR subsidence analysis, but it fetches Sentinel-1 GRD imagery and passes it directly as a displacement raster. This is a semantic data-substitution flaw: users may trust scientifically invalid outputs as real subsidence measurements, which can drive incorrect operational or policy decisions. In this context, the danger is amplified because the script presents authoritative metrics and reports without validating that the input is an actual displacement product.

Context-Inappropriate Capability

Medium

• Confidence: 82% confidence
• Finding: The skill can perform external network acquisition and automatically ingest downloaded data into the analysis pipeline. While not inherently malicious, this expands the trust boundary and can introduce unreviewed remote content, nondeterministic behavior, data provenance issues, and unexpected resource consumption. In a security-sensitive or reproducibility-focused environment, hidden or automatic fetching makes misuse and misinterpretation more likely.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

geoskill-data-fetcher>=0.2.0

# Third-party dependencies used by this skill
numpy
rasterio

• Confidence: 94% confidence
• Finding: numpy

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Third-party dependencies used by this skill
numpy
rasterio

• Confidence: 92% confidence
• Finding: rasterio

Unpinned Dependencies

Low

• Category: Supply Chain

Content

# Requirements for land-subsidence-insar
# Shared data-download library (Planetary Computer / NASA POWER / OSM)
geoskill-data-fetcher>=0.2.0

# Third-party dependencies used by this skill
numpy

• Confidence: 96% 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: 90% confidence
• Finding: numpy

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.