Security audit

Workspace Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill helps organize a ClawPad workspace by creating folders and starter documents, with no evidence of hidden code, credential access, network use, or destructive behavior.

Install this if you want an assistant that can create and organize ClawPad workspace folders and starter Markdown documents. Review proposed structure changes before allowing creation, especially after broad requests like "new project" or "help me organize."

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (3)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger phrases are broad enough to match common requests like 'new project' or 'help me organize', which can cause the skill to activate outside the user's intended context. Because this skill is designed to create folders and documents, over-triggering can lead to unintended workspace modifications and confusing agent behavior.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The onboarding condition relies on vague phrases like 'just set up' or 'help me customize', which are ambiguous and may be unrelated to workspace initialization. In this skill, that ambiguity matters because the workflow proceeds toward creating structures, so a mistaken activation could result in unsolicited changes to the user's workspace.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill instructs the agent to create spaces and a welcome document without clearly warning the user that it will modify the workspace. Silent write behavior is risky because users may interpret the assistant as merely giving advice, while it is actually performing persistent changes.

Static analysis

No suspicious patterns detected.