ClawHub
Back to skill

Security audit

Auto Workflow Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a lightweight, purpose-aligned workflow automation description with broad external-action capabilities that users should treat carefully, but it does not include executable code or hidden behavior.

Install only if you intend to build automations that may contact external services or modify remote systems. Review each workflow before running it, especially anything involving schedules, webhooks, databases, email, SMS, Slack, Discord, or AWS Lambda. Note that this artifact does not include the referenced workflow.sh implementation, so functionality and safeguards would depend on whatever separate tool provides it.

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
  • 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)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill advertises actions such as HTTP requests, email, database operations, and webhooks without any warning that using the skill may transmit data to external services or cause real-world side effects. This can mislead users into invoking workflows that send sensitive data, trigger external systems, or modify remote resources without informed consent.

Vague Triggers

Low
Confidence
84% confidence
Finding
The manifest description says the skill can 'Build automated workflows with no-code visual builder - connect APIs, schedule tasks, trigger actions,' which describes a wide range of common automation intents without defining concrete invocation phrases or boundaries. In a manifest file, this lack of specificity can make activation scope ambiguous and increase the chance of unintended matching.

Static analysis

No suspicious patterns detected.