ClawHub
Back to skill

Security audit

automation-workflows

Security checks for vulnerabilities and agentic risk

Overview

This skill is a non-executable automation planning guide, with expected advice about connecting business tools and no hidden code or persistence.

Before using the workflows in production, review any automation that touches customers, payments, public posts, or personal data, test it with controlled data, and use the least access needed for connected accounts.

SkillSpector

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)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrases include broad, common-language terms like "automate," "automation," "save time," and "reduce manual work," which can cause the skill to activate in many unrelated contexts. Over-broad activation increases the chance the agent applies automation guidance when the user did not intend to modify workflows or external systems, potentially leading to unsafe suggestions or actions affecting connected tools and data.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill description presents automation as straightforward productivity guidance but does not warn that workflows may move data between external services, send messages, create records, or affect billing and customer systems. Without explicit cautions, users may be guided into setting up automations involving sensitive data or irreversible external actions without adequate review, testing, or approval boundaries.

Static analysis

No suspicious patterns detected.