ClawHub
Back to skill

Security audit

BaZi Fortune Hub

Security checks across malware telemetry and agentic risk

Overview

This is a coherent documentation-only integration for a remote BaZi fortune and forum API, with expected privacy and operational caveats but no artifact-backed malicious behavior.

Install only if you intend to send BaZi inputs and authenticated forum actions to fortunehub.lighttune.com.au. Treat birth details and location as personal data, keep the API key server-side, confirm before any forum post/comment, and review or pin any `npx mcp-remote` setup used from the examples.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The walkthrough demonstrates sending highly sensitive personal data, including full birth date, time, gender, and location, to a remote API without any explicit privacy warning, consent guidance, or data-handling notice. In a fortune-reading context these fields are essential for functionality, but they still constitute personal data that could expose users to privacy loss, profiling, or unintended retention if integrators copy the example without adding safeguards.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The example instructs agents to spawn a subprocess (`npx -y mcp-remote`) and send credentialed requests using an API key, but it does not include any safety warning, trust boundary guidance, or constraints on when these actions are appropriate. In an agent-skill context, runnable snippets can be copied into autonomous workflows, so undocumented subprocess execution and external network egress can lead to unreviewed code download/execution, secret exposure to child processes, and unintended outbound actions.

Agent Config Directory Access

High
Category
Agent Snooping
Content
| Agent | Transport | Suspected quirk |
|-------|-----------|-----------------|
| Codex CLI | stdio MCP | Config lives in `~/.codex/config.toml` `mcp_servers` block |
| Cursor | stdio MCP | Default tool timeout tight; same ≥120s guidance for t4 |
| OpenClaw | stdio MCP | Open-source framework; config file format varies per release |
| Hermes | HTTP MCP (SSE or streamable) | Python `mcp` client SDK; check stdio vs SSE support |
Confidence
27% confidence
Finding
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.