ClawHub
Back to skill

Security audit

Educlaw Multi-Subject Agent

Security checks across malware telemetry and agentic risk

Overview

This appears to be a tutoring skill with some weak premium-access design, not evidence of malware or harmful system access.

Install if you want a Chinese-language tutoring helper, but do not treat its activation-code system as secure billing or access control. Publishers should avoid putting codes in prompts and should make triggers more explicit if accidental activation would be disruptive.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The skill embeds paid-access enforcement and hardcoded activation-code verification directly in the prompt, including explicit codes and instructions to persist an authorization flag in memory. For an educational tutoring skill, this is not necessary for core teaching behavior and instead adds business-logic control that can be abused to deny service, bypass platform billing, or leak/normalize secret-like validation material inside the agent behavior.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The documented trigger phrases are short, generic conversational inputs such as '学英语' and '学数学', which can plausibly appear in ordinary user dialogue and accidentally invoke or switch agents. In a routed multi-agent system, overly broad triggers increase the chance of unintended activation, context confusion, and accidental exposure of premium flows or agent-specific behaviors.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.