ClawHub
Back to skill

Security audit

Agentic Workflow Designer

Security checks across malware telemetry and agentic risk

Overview

This appears to be a workflow-automation guidance skill with one broad-trigger concern, but no evidence of hidden access, persistence, credential use, or unsafe behavior.

Install only if you want the agent to route workflow-automation planning requests to this skill. Review any actual automation it helps you design before enabling it in third-party tools, especially workflows that touch business data, customer records, payments, or public posting.

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 (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list contains broad, common phrases such as 'workflow automation', 'n8n', and 'design a workflow' that are likely to appear in ordinary user conversations. This can cause unintended activation of the skill in contexts where the user did not explicitly request it, leading to incorrect routing, over-collection of user context, or unexpected workflow/spec generation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.