ClawHub
Back to skill

Security audit

ClawMart Auto Invoice

Security checks for vulnerabilities and agentic risk

Overview

This is a simple invoice-generation instruction skill with expected financial-data handling and no executable code or hidden behavior.

Install only if you are comfortable giving the agent invoice, customer, bank-account, and tax information. Keep generated invoices and any local storage in a trusted workspace, and avoid entering unnecessary personal or financial details.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill processes and displays highly sensitive financial and personal data, including company details, bank account numbers, tax IDs, customer contact information, invoice status, and receivables, but provides no warning about secure handling, storage, or privacy obligations. This omission can lead users to expose regulated or confidential data through the agent or local storage without understanding the risks.

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
The skill instructions, examples, and output format are presented entirely in Chinese, which effectively imposes a specific language on users. There is no indication that the skill supports other languages, allows user selection, or is intentionally restricted to a Chinese-speaking or region-specific context.

Static analysis

No suspicious patterns detected.