Academic Research Hub

Security checks across malware telemetry and agentic risk

Overview

This skill is a normal academic paper search and download helper, with disclosed network access and user-directed file saving.

Install this in a virtual environment, keep Python dependencies updated, and direct downloads or exports to a dedicated project folder. Treat Google Scholar support as undocumented or unavailable unless the maintainer updates the implementation.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill documents capabilities to write files (`--output`, `--output-dir`, `mkdir -p`) and perform network access to multiple external services, but the manifest does not declare permissions or provide any trust boundaries. This creates a mismatch between apparent behavior and declared capability, increasing the risk of unexpected file modification or outbound data transfer when the skill is invoked.

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The manifest description uses very broad trigger language such as any request involving academic databases, literature reviews, bibliography generation, and research discovery. Over-broad invocation criteria can cause the agent to activate this skill in situations the user did not intend, leading to unnecessary external requests, downloads, or file creation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal