ClawHub
Back to skill

Security audit

CLI Workflow Automator / CLI工作流自动化器

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only CLI automation skill whose powerful examples are disclosed and purpose-aligned, but users should review workflows carefully before running them.

Install only if you are comfortable giving the agent help designing shell workflows. Review every workflow file before execution, especially jobs that upload backups, deploy code, restart services, run on schedules, or use production credentials.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill explicitly promotes automated backups that include remote upload and unattended execution, but it provides no warning about sensitive data leaving the host, credential handling, or the risks of running file and data operations automatically. In a CLI automation context, this omission is security-relevant because users may apply the workflow to production data or secrets and trigger transmission or overwrite actions without adequate review.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill markets deployment, service restart, parallel execution, and scheduled unattended workflows without warning that these actions can disrupt systems, amplify mistakes, or cause destructive changes at scale. In this context, the lack of guardrails is more dangerous because the skill is specifically about chaining shell commands, so a user could automate privileged or production-impacting operations without being prompted to verify safety, scope, or rollback plans.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.