ClawHub
Back to skill

Security audit

skill-0327-02222

Security checks across malware telemetry and agentic risk

Overview

This is a small, disclosed skill for using a summarization CLI, with the main caution that summarized content may be sent to external services.

Before installing, review the upstream summarize CLI or Homebrew formula if you need strong supply-chain assurance. Do not use it on confidential files, private URLs, regulated data, or secrets unless you trust the configured AI provider and any enabled Firecrawl or Apify fallback service.

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 (1)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The documentation explicitly encourages summarizing URLs, local files, PDFs, images, audio, and YouTube content via external model providers and optional fallback services, but it does not warn users that content, metadata, or URLs may be transmitted off-host. This can lead to unintended disclosure of sensitive local documents, private links, or regulated data, especially because multiple third-party services may be involved depending on flags and environment variables.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.