ClawHub
Back to skill

Security audit

Workflow Builder Lite

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed workflow-automation skill that saves user-approved workflows and requires confirmation before higher-risk shell or file actions.

Install this only if you want the agent to create reusable workflow files and help run multi-step automations. Review saved workflows before running them, and be especially cautious approving shell commands, file writes, or workflows that call external APIs or send messages.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (3)

Session Persistence

Medium
Category
Rogue Agent
Content
---
name: workflow-builder-lite
description: "Build and execute multi-step workflows with conditional logic. Chain API calls, agent actions, and shell commands into sequences with if/else branching. Persists workflows to files for reuse. Use when: user wants to plan a multi-step process, automate a pipeline, schedule recurring tasks, or chain together agent actions. Homepage: https://clawhub.ai/skills/workflow-builder-lite"
---

# Workflow Builder Lite v2.0
Confidence
87% confidence
Finding
The skill explicitly supports persistence to files and advertises recurring-task style automation, which creates cross-session state that can be reused later. In this context, persistence is security-relevant because stored workflows may contain action sequences that execute in future interactions, potentially out of the original user's immediate context or after intent has changed.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is broad enough that it could be invoked for many loosely related requests such as automation, planning, scheduling, or chaining actions. In this skill's context, unintended activation matters because the skill is capable of persisting workflows and later executing API calls, agent actions, and potentially shell/file steps, increasing the chance that a user is routed into a higher-risk automation path than intended.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The quick-command trigger phrase "lag workflow" is very generic and could match ordinary conversation about making a process or plan. Because this skill can save persistent workflows and later run multi-step actions, an overly generic trigger raises the risk of accidental activation and unintended workflow creation or execution scaffolding.

Static analysis

No suspicious patterns detected.