ClawHub
Back to skill

Security audit

Editorial Topic Portfolio

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed editorial topic-ranking workflow with guarded Notion read/write boundaries and no evidence of hidden or automatic harmful behavior.

Before installing, confirm you are comfortable giving the skill access to the specific Notion database and credential environment variables it needs. Keep tokens and private mappings outside the skill directory, review the generated change preview, and only enable live writeback after both confirmations.

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 invokes local scripts, reads environment variables for Notion credentials, and reads/writes files, but no explicit permission model is declared. That creates an authorization gap: a runner may grant broader capabilities than reviewers expect, increasing the chance of unintended file or credential access. The danger is moderated by the skill's repeated constraints around secure config and explicit confirmations, but the undeclared capability surface is still real.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.