ClawHub
Back to skill

Security audit

Norman: Manage Clients

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Norman Finance client-management helper, with only a minor caution that its activation wording is somewhat broad.

Install this only if you expect the agent to use the Norman Finance MCP for client records. Because it can list client contact details and balances and create or update records, review actions involving real customer data before approving them, especially creation workflows where the skill does not explicitly require a final confirmation step.

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
96% confidence
Finding
The skill description includes broad activation terms such as 'contacts', 'customers', and 'Kunden', which can cause the agent to invoke this skill in contexts that are only loosely related to client-database management. Over-broad routing increases the chance of unintended access to client records or accidental modification workflows being triggered when the user meant something else.

Static analysis

No suspicious patterns detected.