ClawHub

AI skills for GitHub Copilot, Claude Code, and OpenClaw to generate professional mind maps via the EdrawMind API.

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a legitimate EdrawMind mind-map generator, with the main caution that provided content is uploaded to EdrawMind's online API.

Install only if you are comfortable sending the Markdown, outlines, or project summaries you choose to convert to EdrawMind's online service. Avoid submitting secrets, confidential documents, regulated personal data, or proprietary source details unless you have approval, and keep file or repository access limited to the content you actually want converted.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger condition is extremely broad, matching many common terms such as “思维导图”, “导图”, “mindmap”, and any request to visualize structured information as a tree. This can cause unintended activation on ordinary conversations or adjacent tasks, leading the agent to invoke external tooling and process user or repository content when the user did not clearly request this specific skill.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documentation explicitly describes sending user-provided Markdown to a remote HTTP API, but it does not clearly warn that the content leaves the local environment and may be processed by a third party. In an agent/tool context, this can cause unintended disclosure of sensitive prompts, notes, internal documents, or other private data if users assume the tool is local-only.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The CLI sends user-supplied Markdown to a third-party remote API, but it does not provide a clear runtime warning or consent prompt that the content will leave the local machine. In a CLI context, users may process sensitive notes, plans, credentials, or internal documents and unknowingly disclose them to an external service.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal