ClawHub
Back to skill

Security audit

Page Play Builder

Security checks across malware telemetry and agentic risk

Overview

This SEO planning skill is coherent and disclosed, with limited persistence and gated external actions that fit its stated purpose.

Before installing, be aware that outputs and decisions may be saved into project memory and reused by later agents. Review any off-site publishing, citations, Google Business Profile edits, or index-submission steps before allowing live action, especially where platform terms, business listings, or public SEO pages are involved.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill explicitly writes outputs to `memory/content/`, `memory/hot-cache.md`, and `memory/open-loops.md`, but the top-level description does not clearly warn the user that persistent project memory will be modified. In an agent setting, undeclared persistence can surprise users, cause unintended retention of business data, and make downstream agents act on state the user did not realize was stored.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.