ClawHub

快速草稿

Security checks across malware telemetry and agentic risk

Overview

This is a simple draft-writing helper that stores generated draft history locally, with no evidence of network access, credential use, destructive behavior, or hidden execution.

Install only if you are comfortable with drafts and their input details being saved locally. Avoid highly sensitive personal, legal, medical, or business content unless you know where quick_drafts.json is stored and how to delete it.

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 (2)

Vague Triggers

Medium
Confidence
77% confidence
Finding
The activation phrases are very broad ('草稿 / 写邮件 / 写消息 / 生成') and can match ordinary conversation, causing the skill to trigger unintentionally. In an agent environment, accidental invocation can lead to unwanted processing and local storage of potentially sensitive communications without clear user intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill saves generated drafts, including message bodies and parameters, to a local JSON file automatically without a clear user-facing warning at the point of use. Because drafts may contain names, business topics, schedules, and other sensitive content, silent persistence increases privacy and data exposure risk on shared systems or multi-user environments.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal