Smart Workspace

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:40 PM UTC
• Version:
  1.1.0

Overview

This workspace organizer is instruction-only and clearly discloses automatic workspace folder scanning, project-folder creation, and history updates, but users should expect those changes without per-action confirmation.

Install this only if you are comfortable with the agent automatically scanning top-level workspace folders, creating project folders, and updating PROJECT-HISTORY.md without per-action confirmation. In sensitive or tightly organized workspaces, invoke it explicitly and review the generated history file after first use.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The invocation examples use broad natural-language phrases like 'help me organize the files in my workspace' and 'use smart-workspace to organize and record the files' without requiring explicit confirmation, scope, or path constraints. In the context of a skill that advertises fully automatic workspace scanning and project reorganization, these phrases increase the chance of unintended activation and unintended file moves or metadata changes across the user's workspace.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The 'You Just Say' examples are short, everyday task phrases like 'Analyze football data' and 'Do battery test' that could appear in normal conversation but are described as automatically triggering project categorization. Because the skill auto-creates folders, updates project history, and selects an existing folder on loose keyword matches, ambiguous triggers can cause silent workspace modifications when the user only intended to discuss a task.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The description emphasizes automatic organization and cleanliness but does not clearly warn that the skill may scan the workspace, create folders, and reorganize files based on inferred intent. In this context, omission is security-relevant because users may not realize that ordinary requests can lead to filesystem changes, making accidental data displacement, confusion, or interference with other projects more likely.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill is explicitly designed to create folders and update `PROJECT-HISTORY.md` automatically, without requiring user confirmation. Autonomous modification of workspace state can cause unintended file organization changes, overwrite-like confusion, or persistence of task metadata that the user did not intend to store.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The first-load behavior instructs the agent to scan existing workspace folders and generate a new history file without a user-facing warning. Even if confined to the workspace, this inspects existing project structure and persists derived metadata, which can surprise users and expose prior work context to later automated decisions.

VirusTotal

66/66 vendors flagged this skill as clean.