ClawHub
Back to skill

Security audit

Automation Workflows Conflict

Security checks for vulnerabilities and agentic risk

Overview

This is a plain instructional guide for no-code business automations, with expected third-party workflow risks but no hidden code, persistence, or deception.

Install only if you want guidance on designing no-code automations. Review any proposed workflow before turning it on, especially when it connects customer data, email, CRM, accounting, payments, or public posting tools, and authenticate third-party accounts only when you understand the permissions being granted.

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

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger list includes very broad phrases like "automate," "automation," and "save time," which are common in ordinary conversation and can cause the skill to activate when the user did not intend to invoke it. In a skill that recommends or helps configure external workflows, unintended invocation is risky because it may steer the agent into suggesting actions that affect third-party systems or business processes without clear user intent.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The description does not warn users that automations may move customer or business data into third-party services and may trigger external actions automatically. Because this skill explicitly covers connecting tools, triggers, and actions across platforms, the absence of disclosure can lead users to share sensitive data or approve workflows without understanding privacy, compliance, or operational consequences.

Session Persistence

Medium
Category
Rogue Agent
Content
2. Flag customers with <50% of average usage
  3. Add flagged customers to "At Risk" segment in CRM
  4. Send re-engagement email campaign to at-risk customers
  5. Create task for me to personally reach out to top 10 at-risk customers
```

### Invoice and payment tracking
Confidence
80% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Static analysis

No suspicious patterns detected.