ClawHub
Back to skill

Security audit

Workflow Refactor

Security checks across malware telemetry and agentic risk

Overview

This appears to be a workflow/process-refactoring guidance skill with broad activation wording but no evidence of code execution, credential access, persistence, or hidden data handling.

Install only if you want the agent to apply a process-refactoring mindset to workflow-help requests. Be aware it may activate on generic optimization or simplification prompts; review its suggestions before applying them to real business processes.

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
92% confidence
Finding
The trigger list is very broad and includes common phrases such as process improvement, optimization, simplification, and reorganization. This can cause the skill to activate for ordinary workflow-help requests outside the user's intent, increasing the chance that the agent applies a strong workflow-rewrite frame inappropriately and overrides more suitable domain-specific guidance.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The rule that users can trigger refactoring whenever they 'feel the process is too complex' is ambiguous and subjective. In practice this weakens activation boundaries, making the skill easier to invoke in situations where the user did not clearly request this methodology, which can lead to scope capture and misapplication of the skill's restructuring rules.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.