Back to skill

Security audit

票据整理与报销台

Security checks for vulnerabilities and agentic risk

Overview

This is a simple invoice and reimbursement organization skill with no code execution, network access, credential use, persistence, or hidden behavior found.

Before installing, be aware that this skill is meant for reimbursement and invoice整理 only. Avoid sharing unnecessary personal, tax, or business-sensitive details, and verify tax or reimbursement conclusions with your accountant, company policy, or the relevant authority. The broad trigger examples could route a generic table-formatting request into this skill, so invoke it deliberately for invoice or reimbursement tasks.

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
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger examples include short, generic phrases like “报销单” and “财务报销” that are common in ordinary conversation and may activate the skill when the user did not explicitly intend to invoke it. In a finance-related skill, unintended activation can expose sensitive invoice or reimbursement details to the wrong workflow and cause privacy or data-handling issues.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language examples are broad and could match many routine requests, such as ‘把这些整理成一张表’, which is not unique to invoice processing. This increases the risk of accidental routing of unrelated or sensitive business content into the skill, especially because the skill handles financial and potentially personal data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.