ClawHub
Back to skill

Security audit

Automation Workflows

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown guide for designing no-code business automations, with no executable code or hidden install behavior.

Before installing, treat this as a general automation playbook. When following its examples, use least-privilege app permissions, test with non-sensitive data first, add duplicate/error checks, and manually review workflows that send emails, update CRMs, or touch invoices and payments.

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
95% confidence
Finding
The trigger list includes broad phrases such as "automate," "automation," and "save time," which can match many unrelated user requests and cause unintended invocation of this skill. Misrouting can lead the agent to suggest or initiate automation-oriented handling in contexts where the user did not intend it, increasing the chance of inappropriate actions or data-handling advice.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The skill provides detailed guidance for connecting forms, CRMs, email tools, payment systems, and customer data flows, but does not warn about privacy, consent, authentication scope, or data-integrity risks. In an automation context, missing warnings can cause users to create workflows that expose personal data, send incorrect communications, or silently corrupt records across systems.

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.