ClawHub
Back to skill

Security audit

Norman: Accounting Monthly Reconciliation

Security checks for vulnerabilities and agentic risk

Overview

This skill guides month-end accounting reconciliation through a disclosed finance MCP and requires user confirmation before sensitive final actions.

Before using this skill, confirm the exact month and review each proposed categorization, verification, reminder, and tax action carefully because it can modify accounting records and initiate finance workflows through the Norman Finance MCP.

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
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description and usage text include broad phrases like 'monthly bookkeeping' and 'Monatsabschluss', which can cause the skill to trigger for general accounting requests rather than only explicit month-end reconciliation. In a financial skill with capabilities to verify transactions, link invoices, send reminders, and prepare tax workflows, over-broad activation increases the chance of unintended high-impact actions being initiated in the wrong context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.