ClawHub
Back to skill

Security audit

Teaching Diagram Maker

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward diagram-making helper that edits nearby notes and image files as part of its stated purpose.

Install this if you want an assistant to create and repair teaching diagrams in your notes. Be aware it may edit nearby note text, add image files, embed links, and render previews, so use it on content where those changes are acceptable.

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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The default prompt is broad enough to match many ordinary requests about explaining concepts visually, which can cause the skill to be invoked implicitly in situations the user did not clearly request. Because the skill also instructs embedding content and visually verifying rendered output, unintended invocation could expand data exposure and tool use beyond user expectation.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrases "draw a diagram" and "explain this visually" are broad, natural-language requests that can appear in many unrelated conversations. This can cause accidental invocation of the skill in contexts where diagram generation was not intended, increasing the attack surface for prompt interference, unintended data handling, or workflow disruption.

Vague Triggers

Low
Confidence
82% confidence
Finding
The invocation description and trigger set do not clearly bound when the skill should versus when a general-purpose assistant should answer normally. This ambiguity can lead to over-triggering across common requests, making the skill more likely to run on irrelevant inputs and increasing the chance of unintended behavior or exposure of user content to unnecessary processing.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.