ClawHub
Back to skill

Security audit

AI 体检报告解读

Security checks across malware telemetry and agentic risk

Overview

This skill is coherent as a health-report interpreter, but it handles sensitive medical information with broad activation phrases and insufficient privacy/user-control warnings.

Install only if you are comfortable using an AI assistant on sensitive health data. Redact names, ID numbers, phone numbers, hospital IDs, and other identifiers before use, treat generated HTML reports as private, and rely on a qualified clinician for diagnosis or treatment decisions.

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
92% confidence
Finding
The trigger phrases are broad and include common conversational language such as '看不懂报告' and '帮我看看体检', which can cause the skill to activate in situations where the user did not explicitly intend to invoke a medical-report interpreter. In a health-related context, accidental activation is more sensitive because it may steer users into receiving quasi-medical guidance or disclosing personal health information without clear intent.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger list contains broad, common phrases such as 'health checkup' and '报告解读' that may cause the skill to activate in contexts the user did not intend. In a medical-report skill, accidental invocation is more sensitive because users may expose health information or receive medical-style guidance without explicitly choosing this workflow.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill handles highly sensitive medical report data and generates HTML output that may be saved or shared, but the description does not warn users about privacy risks. This increases the chance that users will submit personally identifiable health information without understanding retention, sharing, or exposure risks, making the context materially more dangerous than ordinary content processing.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.