Security audit

GEDCOM Explorer

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a local GEDCOM-to-HTML family tree generator, with privacy cautions around the generated file and one external font request.

Use this only with GEDCOM files you intend to process, and treat the generated HTML as private because it embeds family-history data. Review or redact living-person details before sharing, emailing, syncing, or hosting the output. For stricter privacy, remove or block the Google Fonts link so opening the dashboard does not contact Google.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 87% confidence
Finding: The skill documentation indicates file read/write behavior but does not declare permissions, which weakens transparency and consent around access to local GEDCOM inputs and generated HTML outputs. In a genealogy context this is sensitive because GEDCOM files can contain extensive personal and family-history data, so undeclared file capabilities increase the chance of overbroad or surprising data handling.

Description-Behavior Mismatch

Medium

Confidence: 93% confidence
Finding: The generated HTML is advertised as a single-file dashboard, but it loads Google Fonts from an external CDN. Opening the output file therefore triggers a network request that can leak metadata such as viewing time, IP address, and possibly the fact that a genealogy file was opened, which is sensitive in this skill's family-history context.

Vague Triggers

Medium

Confidence: 76% confidence
Finding: Broad trigger phrases like 'family tree' or 'ancestors' can cause the skill to activate in contexts where the user did not intend to process or expose genealogy data. In this skill, unintended invocation is more sensitive than usual because the output bundles potentially private family information into a portable HTML file.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill does not warn users that the generated single-file HTML embeds the full genealogy dataset inline, making it easy to copy, upload, email, or host sensitive family records unintentionally. In genealogy workflows this is particularly dangerous because GEDCOM files may include names, birth/death details, places, and relationship data for living or recently deceased individuals.

Missing User Warnings

Medium

Confidence: 83% confidence
Finding: The tool writes a complete HTML file containing potentially sensitive genealogy data to disk without any privacy warning, minimization, or safer-default handling. In this context, family-history data can include names, dates, places, and relationships, so silently persisting it increases the risk of unintended disclosure through shared machines, backups, sync services, or later redistribution.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.