ClawHub
Back to skill

Security audit

skill-0327-04

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward summarization skill, but users should remember that chosen files or URLs may be processed by external AI and extraction services.

Install only if you are comfortable sending the URLs, documents, media, or extracted text you choose to summarize to the configured provider and possible fallback services. Avoid confidential, regulated, private, or customer data unless your organization has approved those providers and review any API keys and ~/.summarize/config.json you configure.

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
94% confidence
Finding
The skill explicitly supports summarizing URLs, local files, and YouTube content using external model providers and optional third-party extraction services, but it does not warn users that submitted content may be transmitted off-device. This creates a real confidentiality and privacy risk because users may pass sensitive local documents, internal URLs, or restricted media to external APIs without informed consent.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.