ClawHub
Back to skill

Security audit

Anygen Diagram Tool Free

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a diagram-generation wrapper, but its instructions are overbroad enough that it may be invoked for unrelated API or webhook work while using an external CLI service.

Install only if you are comfortable using the AnyGen CLI and sending diagram descriptions to AnyGen services. Avoid using it for webhook setup, API integration, system connection work, secrets, private architecture details, or any task outside diagram generation unless the publisher narrows the instructions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The skill is presented as a diagram-generation tool, but the documented capability model introduces broad create/query/modify/delete, import/reset, and export/convert operations that are not scoped to diagram rendering. This kind of semantic overreach can cause an agent to invoke the skill for unrelated tasks or pass arbitrary user data into an external CLI/API, increasing the chance of unintended actions and data exposure.

Description-Behavior Mismatch

Medium
Confidence
94% confidence
Finding
The trigger conditions instruct use for API integration, interface docking, webhook configuration, and system connection tasks, which materially exceeds the stated purpose of a personal diagram generator. In an agent environment with exec access, this mismatch can cause inappropriate invocation during sensitive integration workflows, leading to external calls, credential handling, or command execution in contexts the user did not intend.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger description is inconsistent with the actual functionality and is overly broad, making misrouting and over-invocation more likely. When a skill with exec capability is triggered by vague integration-related prompts, the agent may execute external commands or initiate authentication flows outside the user’s intended diagram task.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The skill states that rendering is performed server-side and depends on an external API, but it does not clearly warn that user-provided diagram descriptions may be transmitted to third-party services. This creates a privacy and data-governance risk, especially if users include architecture details, internal system names, or other sensitive content in natural-language prompts.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.