ClawHub
Back to skill

Security audit

复习规划师

Security checks across malware telemetry and agentic risk

Overview

This is a Markdown-only teacher review-planning skill whose data use and write-back behavior are disclosed and aligned with its educational purpose.

Before installing, users should be aware that this skill is intended to work with student-analysis and exam-design context. Use it with aggregated or de-identified student performance data, and avoid feeding it individual rankings, sensitive student records, or mental-health details beyond general classroom study-strategy concerns.

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
90% confidence
Finding
The trigger examples in the metadata description use broad natural-language phrases such as '帮我安排复习计划' and '期末怎么复习', which can cause the platform to activate this skill for loosely related requests without checking whether the user actually wants structured review planning. This is not a code-execution issue, but it can lead to scope confusion, unintended data access through dependent skills, or bypass of more appropriate specialized skills.

Vague Triggers

Low
Confidence
84% confidence
Finding
The '触发时机' section lists positive trigger scenarios but does not define clear exclusions or non-trigger cases, so the skill boundary is underspecified. In a multi-skill environment, this increases the chance of over-triggering, misrouting user requests, and unnecessarily pulling in student-analysis or exam-planning context when a simpler response would suffice.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.