ClawHub
Back to skill

Security audit

Bazi Qimen

Security checks across malware telemetry and agentic risk

Overview

This is a local Bazi and Qi Men chart-reading skill with some broad activation wording, but no evidence of hidden access, persistence, network use, or destructive behavior.

Install this only if you want traditional Chinese metaphysics chart calculations. Treat career, wealth, relationship, and health readings as cultural reference material, not professional advice, and clarify Bazi, Qi Men, or both if the skill activates on a vague request.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list includes generic terms like "interpretation," "pattern," and "chart calculation," which are broad enough to match unrelated user requests and cause unintended activation of this skill. In an agent environment, overbroad activation can route sensitive or irrelevant queries into this skill, leading to confusing outputs, privacy issues from unnecessary data collection, or interference with safer/more appropriate skills.

Vague Triggers

Medium
Confidence
89% confidence
Finding
When intent is unclear, the skill instructs the agent to default to Bazi and then supplement with Qi Men, which effectively expands the scope without explicit user consent. This ambiguous fallback increases the chance of unsolicited tool use, unnecessary processing of personal birth/time data, and incorrect routing of user requests into a metaphysical workflow they did not ask for.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.