ClawHub

Craft CLI

Security checks across malware telemetry and agentic risk

Overview

This skill is a real Craft document CLI wrapper, but it includes specific personal and business Craft API links and can modify or delete documents, so it should be reviewed before use.

Install only if you intentionally want this skill to use the listed Craft spaces. Replace the hardcoded API URLs with your own scoped Craft endpoint, verify the GitHub binary before installing it with sudo, check the active Craft space before every command, and require explicit approval before update or delete operations.

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 (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill documents a destructive `delete` operation with no warning about irreversible data loss, no recommendation to verify the target document ID, and no guidance to require explicit user confirmation before execution. In an agent setting, this increases the chance of accidental or unauthorized deletion of remote documents because the skill normalizes destructive behavior as a routine command.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The configuration examples direct the user to connect the CLI to remote Craft API endpoints, including a business space and a personal space, without any privacy or data-handling warning. Because subsequent commands can list, search, retrieve, create, and update documents against those endpoints, the skill may encourage agents or users to send potentially sensitive document metadata and content to remote services without informed consent or boundary checks.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal