ClawHub
Back to skill

Security audit

写作教学指导

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed teaching-support skill for Chinese composition instruction, with no executable code or hidden install behavior found.

Before installing, confirm that your classroom workflow is comfortable with storing or passing pseudonymized student writing profiles between related teaching skills, and use the included privacy boundaries for consent and de-identification.

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
93% confidence
Finding
The metadata description contains very broad trigger phrases such as '这周写什么作文' and '怎么批改作文', which are common classroom queries and can cause the skill to activate in situations where a more specific teaching, grading, or planning skill would be more appropriate. Overbroad activation increases the chance of unintended routing, unnecessary access to student-related context, and workflow confusion across dependent skills.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger section lists many ambiguous activation conditions without disambiguation rules, so the skill may be invoked for loosely related requests like '学员不会写怎么办' or '写不出来' that could belong to counseling, tutoring, or broader classroom support workflows. In a multi-skill environment, this can cause accidental activation, misrouting of user requests, and inappropriate propagation of student-analysis data to downstream integrations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.