科研学术助手

Security checks across malware telemetry and agentic risk

Overview

This is a coherent academic writing helper; its document processing and optional web search fit the stated purpose, though users should be careful with confidential research material.

Install only if you are comfortable having selected papers, notes, or literature data processed by the agent. Avoid uploading unpublished, proprietary, embargoed, reviewer, regulated, or personally sensitive material unless you have approval, and enable online literature search only for topics or queries you are willing to send externally.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill encourages users to upload academic documents and says text will be extracted automatically, but provides no warning about sensitive content, retention, or downstream processing. Research papers, drafts, peer reviews, and unpublished results can contain confidential or embargoed information, so silent ingestion increases privacy and data-handling risk.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill advertises online literature search but does not warn users that network-enabled queries may disclose research topics, search terms, or document-derived context to external providers. For academic users, this can leak unpublished directions, grant themes, or proprietary research interests.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal