BaZi Fortune Hub

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed remote BaZi fortune-reading and forum MCP gateway, with expected API-key, billing, personal birth-data, and forum-write behavior documented.

Install only if you are comfortable using Fortune Hub as a third-party service. Keep the API key server-side, get user consent before sending exact birth details, and require explicit confirmation before creating posts or comments because those actions persist publicly or semi-publicly on the forum.

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 (3)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger scope includes generic actions like posting, listing posts, commenting, and liking that are not tightly constrained to BaZi or fortune-reading contexts. This can cause an agent to route broadly applicable social/forum requests to this external skill, increasing the chance of unnecessary external API use and unintended write actions on a third-party service.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The walkthrough instructs integrators to send highly sensitive personal data (full birth date/time, gender, and location) to a remote third-party API, but this file provides no privacy warning, consent guidance, retention notice, or data-handling caveat. In a fortune-reading context, this is especially sensitive because exact birth details are the core input and are personally identifying enough to create privacy and compliance risk if users are not clearly informed.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The manifest description advertises both fortune-reading and forum/community functions without clearly constraining when community actions should be used. In an agent setting, broad capability descriptions can cause over-invocation of posting, commenting, or liking features, increasing the risk of unintended data sharing, spam, or user actions taken without clear consent.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal