Familysearch

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed genealogy helper that reads user-provided GEDCOM files or queries FamilySearch with a user token, with no evidence of hidden data theft or persistence.

Install only if you are comfortable letting the agent read GEDCOM files you explicitly provide and, in API mode, use your FamilySearch OAuth token to query FamilySearch. Avoid sharing GEDCOM files or outputs containing living relatives in shared terminals, logs, or chats unless you are comfortable exposing those details.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger list includes broad phrases such as 'family tree', 'genealogy', and 'FamilySearch', which are likely to match ordinary conversation and cause the skill to activate unexpectedly. Because this skill can prompt for credentials, process highly sensitive family-history data, and potentially send data to an external API, over-broad triggering increases the chance of unintended handling or disclosure of personal information.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill description does not warn users that family-history data may include sensitive personal information about living relatives and that API mode transmits queries to FamilySearch. Without a clear warning and consent step, users may unknowingly expose names, relationships, birth/death details, and other genealogical data to a third party.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal