ClawHub
Back to skill

Security audit

Norman: Create Invoice

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward invoice-creation workflow with disclosed Norman Finance access and no hidden code or persistence.

Install only if you intend Codex to create invoice records in Norman Finance. Review the collected client, line items, VAT, dates, and amount before allowing the workflow to proceed, and only approve sending when the invoice is ready to email.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description and usage scope are broad enough that it could be invoked for common billing-related requests without strong boundaries or confirmation gates. Because this skill can create and optionally send invoices, over-broad triggering increases the risk of unintended financial actions, especially if the agent misclassifies a user request as authorization to invoice or send billing communications.

Static analysis

No suspicious patterns detected.