ClawHub
Back to skill

Security audit

patent-portfolio-report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed patent-report workflow that uses Patsnap patent searches to generate Chinese HTML reports, with no hidden execution, persistence, or unrelated data handling found.

Install this only if you are comfortable authorizing Patsnap MCP access and sharing the target companies, patent lists, competitors, and business questions needed for the report. Expect Chinese HTML output unless you modify or override the skill instructions.

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
  • 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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill metadata and content repeatedly require Chinese-only output for the final report without stating that this is conditional on user preference. Hard-forcing a language can override the user's explicit choice, reduce transparency for multilingual users, and create prompt-control issues where the skill constrains agent behavior beyond the user's intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.