ClawHub
Back to skill

Security audit

Design Md

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Markdown diagram helper, with the main caution that it may run dependency checks or global install commands if tools are missing.

Install only if you are comfortable letting the agent create or modify Markdown-adjacent files under .mddoc and run mddoc/d2 commands. If mddoc or d2 are missing, review the global npm/brew/winget install step first, or install those tools yourself before using the skill.

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 (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrases include very generic terms like "diagram" and "插入图表", which can match ordinary editing requests and cause the skill to activate unexpectedly. Because the skill has Write, Read, and Bash permissions and instructs dependency checks/install commands, accidental activation can lead to unintended file modifications or command execution in contexts where the user did not explicitly ask for this skill.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal