Security audit

Geoskill: Coastline Change Monitor

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent coastline analysis tool with disclosed local processing and a documented optional remote-download mode, but users should be aware of network access and unpinned geospatial dependencies.

Install this only if you are comfortable with a geospatial tool that can read local shoreline/raster files, write analysis outputs, and optionally contact Microsoft Planetary Computer when bbox/date inputs are used. For enterprise or sensitive locations, require explicit approval for network mode, set a controlled output/cache directory, and pin or lock dependencies before production use.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (11)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 92% confidence
Finding: The skill is presented as operating on user-provided shoreline files, but the documentation also indicates additional behaviors including automatic remote data download and other processing modes not clearly declared in the primary description. This hidden expansion of capability is dangerous because it can trigger unexpected network access and broader data handling than a user or orchestrator would authorize.

Description-Behavior Mismatch

Medium

Confidence: 90% confidence
Finding: The documentation claims the skill analyzes provided shoreline files, but later states it can automatically fetch remote data from Microsoft Planetary Computer when only bbox/date parameters are supplied. This discrepancy can cause unanticipated outbound requests and processing of externally sourced data, which is a meaningful security and governance concern in constrained agent environments.

Description-Behavior Mismatch

Medium

Confidence: 84% confidence
Finding: The requirements declare a shared data-download library with access to external sources, but the skill description presents the capability as analytics-focused shoreline analysis. This mismatch can hide network-enabled behavior from reviewers and users, expanding the attack surface through remote data retrieval, SSRF-like misuse, or unexpected exfiltration paths if the dependency is invoked by the skill.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The markdown describes automatic remote data download but gives no warning that using bbox/date inputs may initiate outbound network access or transmit query parameters to an external service. In agent or enterprise contexts, silent network behavior is dangerous because it can violate user expectations, privacy constraints, or execution policies.

Unpinned Dependencies

Low

Category: Supply Chain
Content: geoskill-data-fetcher>=0.2.0 # Third-party dependencies used by this skill fiona numpy rasterio shapely
Confidence: 90% confidence
Finding: fiona

Unpinned Dependencies

Low

Category: Supply Chain
Content: # Third-party dependencies used by this skill fiona numpy rasterio shapely
Confidence: 90% confidence
Finding: numpy

Unpinned Dependencies

Low

Category: Supply Chain
Content: # Third-party dependencies used by this skill fiona numpy rasterio shapely
Confidence: 88% confidence
Finding: rasterio

Unpinned Dependencies

Low

Category: Supply Chain
Content: fiona numpy rasterio shapely
Confidence: 87% confidence
Finding: shapely

Unpinned Dependencies

Low

Category: Supply Chain
Content: # Requirements for coastline-change-monitor # Shared data-download library (Planetary Computer / NASA POWER / OSM) geoskill-data-fetcher>=0.2.0 # Third-party dependencies used by this skill fiona
Confidence: 91% 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: 95% 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: 93% confidence
Finding: numpy

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.