ClawHub
Back to skill

Security audit

automation-workflow-builder（自动化工作流构建器，设计并执行跨平台自动化流程，支持定时触发、文件监控、多步骤操作。适用于数据同步、内容发布、报告生成。）

Security checks across malware telemetry and agentic risk

Overview

This automation skill is not visibly malicious, but it asks for broad command, file, network, and messaging powers without enough limits or approval guidance.

Install only if you will review each workflow before it runs. Keep it limited to a specific workspace, require explicit approval for shell commands, file moves or overwrites, uploads, public posting, and messaging, and avoid unauthenticated webhooks or recurring jobs without a clear way to disable them.

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 (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly advertises high-impact capabilities including file write/move, network requests, and command execution, but does not describe any guardrails such as user confirmation, path restrictions, allowlists, or consent before destructive or external actions. In an automation skill, these capabilities materially increase the chance of unsafe workflows causing data loss, unintended system changes, or exfiltration if invoked from ambiguous or attacker-influenced inputs.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list contains broad generic terms such as "automation", "workflow", and "cron", which can cause the skill to be invoked in contexts far beyond the author's likely intent. Because this skill exposes high-risk capabilities like exec, read, write, and web_fetch, accidental or overly broad invocation increases the chance that sensitive operations are performed when a user did not explicitly request this skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.