Back to skill

Security audit

patent-infringement-watch

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed patent-infringement analysis workflow that uses patent, web, and file tools in ways that match its stated purpose, with no hidden execution or persistence found.

Before installing, confirm you are comfortable authorizing the required patent MCP service and letting the agent process uploaded competitor product files and public web sources. Treat the output as a research aid only, not legal advice, and have a qualified patent professional review any high-impact conclusion.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

There is a clear description-behavior mismatch. The declared purpose describes a substantive patent infringement analysis workflow, but the actual code is only a minimal placeholder entry script with no inputs, no data access, no analysis logic, and no reporting capability. The primary purpose and implemented behavior are materially different.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description and all user-facing instructions are presented only in Chinese, with no indication that users may choose another language or locale. Under the policy, language constraints should be opt-in or explicitly justified as region-specific; neither is stated here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.