ClawHub
Back to skill

Security audit

职业与健康命理分析

Security checks across malware telemetry and agentic risk

Overview

This is a local astrology-style career and health analyzer with some privacy and medical-disclaimer gaps, but no evidence of hidden access, persistence, or data sharing.

Install only if you are comfortable giving the agent birth date, birth time, and gender for fortune-style analysis. Treat all health output as entertainment or general wellness commentary, not diagnosis or treatment advice, and consult a qualified clinician for real symptoms or concerns. If running the Python code, verify any missing dependency such as sxtwl from a trusted source.

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 (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes very broad, common phrases such as '职业分析' and '健康分析' that can overlap with ordinary user conversations, increasing the chance of unintended activation. In a skill that processes sensitive birth and health-related data, accidental invocation can lead to unnecessary collection or handling of personal information and confusing responses in unrelated contexts.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill invites users to submit birth date, time, sex, and health-related information but provides no warning about the sensitivity of this data or how it will be handled. This creates privacy and compliance risk because users may disclose highly sensitive personal information without informed consent or understanding of retention, sharing, or limitations of the analysis.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This code generates personalized health risk conclusions and body-organ warnings based on user inputs, but it does not present any disclaimer that the output is not medical advice. In a health-related skill, users may reasonably treat these statements as diagnostic guidance, which can lead to unsafe self-treatment, delayed care, or unwarranted anxiety.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.