ClawHub
Back to skill

Security audit

Workspace Manager

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward workspace organizer that creates folders and starter documents, with no evidence of hidden code, credential access, exfiltration, or destructive behavior.

Install this if you want an agent to help set up and maintain a ClawPad workspace. In an existing or important workspace, ask it to preview the exact folders and files before creating them, because its intended behavior is to add persistent workspace structure and markdown documents.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (4)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrases are broad enough to match many ordinary organizational requests, which can cause the skill to activate unexpectedly outside the user's intended context. In a skill that creates folders and documents, overbroad activation increases the chance of unanticipated workspace modifications and confusing or unsafe automation.

Vague Triggers

Low
Confidence
76% confidence
Finding
The onboarding condition is described inconsistently ('just set up', 'new workspace', 'help me customize'), making activation logic ambiguous. That ambiguity can cause the skill to enter setup mode when the user only wanted advice, increasing the risk of unintended writes or structural changes.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
These instructions direct the agent to create folders and a welcome document immediately after the user responds, but they do not require disclosure or confirmation that files will be written. In a workspace-management skill, silent modification of the user's filesystem or workspace content is risky because it can create clutter, overwrite expectations, or violate user intent.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The project-creation flow instructs the skill to create a folder and initial files as part of handling a 'new project' request, but it does not require any warning that the workspace will be modified. Because this skill's core function is organization, the danger is contextual rather than inherently malicious, but the lack of explicit consent still makes unintended writes plausible and harmful.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.