ClawHub
Back to skill

Security audit

Design

Security checks across malware telemetry and agentic risk

Overview

This is a design guidance skill with limited, disclosed local preference memory and no hidden execution or data exfiltration found.

Before installing, be aware this skill may keep design preferences and project context in ~/Clawic/data/design/. Review or delete those files if you do not want design memory retained between tasks.

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
97% confidence
Finding
The skill explicitly instructs the agent to read from and write to files under the user's home directory, including persistent preference and memory files, without requiring user notice or consent at the time of access. Even though the data appears related to design preferences, this creates silent persistence and retrieval of user data, which can expose sensitive information, leak prior context across tasks, or modify local files in ways the user did not expect.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.