ClawHub

Ruankao Essay Writing | 软考论文写作

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a writing-guidance skill with a broad activation phrase issue, but there is no evidence of hidden access, persistence, credential handling, destructive behavior, or data exfiltration.

This looks acceptable to install for its stated writing-help purpose. Be aware that it may activate for general paper-writing or revision requests, so check that the skill is being used in the intended exam-essay context before relying on its output.

Publisher note

覆盖软考系统架构设计师论文写作全流程（项目准备→试题分析→提纲撰写→摘要撰写→正文填充→检查校对），提供 SCQA 框架、金字塔原理、素材库建设等专业指导。当用户提到"帮我写论文""论文指导""如何准备论文""改论文""论文提纲""论文模板"等涉及论文写作的需求时触发。不适用于论文评分（那是 ruankao-essay-scoring 的职责）。

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
94% confidence
Finding
The trigger phrases include very broad expressions such as “帮我写论文”, “论文指导”, and “改论文”, which can match many general writing or academic-assistance requests outside the intended soft-exam architecture-essay context. This can cause unintended skill activation, leading to scope confusion, inappropriate responses, or routing sensitive/irrelevant user content into a specialized workflow that was not meant for it.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal