Back to skill

Security audit

patent-transfer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed patent-analysis report generator that uses expected patent, company, and news data sources to produce an HTML brief.

Before installing, confirm you are comfortable authorizing the required PatSnap/Zhihuiya MCP services and sending patent numbers, company names, and industry context to the configured external data providers. Treat generated reports as business-sensitive internal material and verify cited patent events or news before outreach.

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
  • 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 (3)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 111)May include surrounding context.

md
</head>
<body>
<div class="report-container">
  <!-- 头部信息 -->
  <div class="header">
    <h1>专利资产运营转化监测简报</h1>
    <div class="subtitle">Technology Transfer Intelligence Report | {{industry}}领域专利包</div>

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 111)May include surrounding context.

md
</head>
<body>
<div class="report-container">
  <!-- 头部信息 -->
  <div class="header">
    <h1>专利资产运营转化监测简报</h1>
    <div class="subtitle">Technology Transfer Intelligence Report | {{industry}}领域专利包</div>

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language description and role instructions are written entirely in Chinese and define the skill persona/output behavior in Chinese, without any note that the user may choose another language. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation unless the restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.