ClawHub

Excalidraw Tech Illustration

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Excalidraw diagram generator whose file creation and collection-index updates fit its stated purpose.

Install this if you want an agent to generate Excalidraw technical diagrams and organize them in an excalidraw/collection tree. Be aware that it can modify project files by adding diagrams, updating index.json statistics, and creating README files, and that the rendering command uses an external npx CLI.

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
90% confidence
Finding
The trigger conditions include broad phrases like '生成配图', '流程图', and '架构图', which are common in normal conversation and can cause the skill to activate when the user did not intend to invoke it. Unintended activation can lead to unnecessary file generation and repository modifications, especially because the skill also mandates follow-on file operations.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The fallback rule '无明确关键词 → 默认 A 纵向流程图' effectively permits activation even when the user's request does not clearly match the skill's intended scope. This increases the chance of accidental invocation and compounds risk because the skill is designed to create, move, and index files automatically.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill requires moving generated files into repository paths and updating collection metadata files, but it does not indicate that these are side effects requiring user awareness or consent. In an agent environment, silent repository writes can alter project state, overwrite curated indexes, or create persistence that the user did not request explicitly.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal