ClawHub
Back to skill

Security audit

软考高级·系统规划与管理师论文辅助

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed exam-essay framework helper that uses local templates and optional scoped knowledge-base lookup without hidden persistence or destructive behavior.

Before installing, be aware that optional IMA lookups may use a separate knowledge-base integration; use them when you want exam-prep retrieval, and provide only project details you are comfortable sharing. The skill instructs the agent not to invent projects or copy source essays, but users should still review outputs for originality and accuracy.

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 (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger conditions are broad enough that normal discussion of exam essays or outlines could activate the skill unexpectedly, especially because README only lists example phrases and does not define exclusions or confidence thresholds. Unintended activation can cause the assistant to route unrelated user input into this skill, increasing the chance of inappropriate retrieval, confusing responses, or bypass of a more suitable safer skill.

VirusTotal

45/45 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.