Academic Research and Paper Writing Assistant

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only academic writing helper with no evidence of hidden execution, data collection, persistence, or credential use.

Install only if you want academic drafting and research-planning help, especially in Chinese. Treat its literature, journal metrics, funding, statistics, ethics, and AI-disclosure guidance as draft support and verify important decisions against current authoritative sources.

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 section uses broad example phrases such as '帮我做XX方向的文献综述' and '帮我写论文的Methods部分' without defining scope limits, exclusions, or precise routing criteria. This can cause the skill to activate unexpectedly for loosely related academic requests, increasing the chance of misrouting user input, overriding more appropriate safeguards, or being invoked in contexts the author did not intend.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill metadata and description are written as Chinese-language-first and do not document any user locale negotiation or opt-in behavior. This can lead to responses in an unexpected language, causing misunderstanding of research, ethics, or statistical guidance, especially where precision matters.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal