Back to skill

Security audit

map-competitive-patent-landscape-ip

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed patent-landscape research workflow that uses PatSnap tools and writes a local HTML report without hidden persistence or destructive behavior.

Before installing, confirm you are comfortable using PatSnap MCP tools for the research because queries and report context may include competitor, technology, and possibly client information. Keep PatSnap API keys out of reports, prompts, logs, and source control, as the skill itself also instructs.

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

Yes, this is a mismatch. The declared purpose promises a substantial analytical capability around competitive patent landscaping, but the supplied code chunk does not implement any of that behavior. Instead, it merely prints a static message when executed. This is a materially different primary purpose from the description, and the described capabilities are absent from the code shown.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The visual standard explicitly requires a Western font stack and excludes specific East Asian fonts as primary global fonts. This is a natural-language locale/style restriction that can disadvantage non-Western language presentation and is not presented as an opt-in or region-specific compliance need.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.