ClawHub
Back to skill

Security audit

Literature Review

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward literature-search helper that contacts named academic databases and does not show hidden or destructive behavior.

Before installing, be comfortable with your literature queries and optional contact email or API keys being used with Semantic Scholar, OpenAlex, Crossref, and PubMed. Use dedicated low-privilege API keys and a non-sensitive contact email if you configure them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill explicitly describes use of environment variables and outbound network access to multiple external APIs, yet no declared permissions are present. This creates a permissions mismatch: a host system or reviewer may underestimate the skill’s access needs, reducing transparency and increasing the risk of unintended data exposure via env vars or remote requests.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.