ClawHub
Back to skill

Security audit

Content Ingestion Demo

Security checks across malware telemetry and agentic risk

Overview

This skill openly turns a user-chosen file into a publishable skill package, but users should review the package because it includes the original file and metadata.

Only run this on files you are comfortable including in a publishable skill package. Before sharing or publishing the generated folder, review references/ and assets/metadata.json, and remove private content or local path details if they should not be disclosed.

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

Medium
Confidence
87% confidence
Finding
The skill explicitly states it copies the input file into references/ and stores source_path, size, sha256, and timestamps in metadata, but the description does not warn users that potentially sensitive content and local filesystem metadata will be preserved in the generated package. This can lead to unintentional disclosure of private document contents, internal path structures, or provenance data when the package is shared or published.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.