ClawHub
Back to skill

Security audit

mab-fto-check

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed patent-FTO workflow that relies on user-authorized PatSnap/MCP tools and local report files, with no hidden persistence or exfiltration found.

Install only if you intend to use PatSnap/Zhihuiya MCP tools for patent FTO work and are comfortable sending antibody sequences and business context to those authorized services. Treat generated conclusions as decision support, not legal advice, and require source-backed claim text plus attorney review before relying on the report.

SkillSpector

By NVIDIA
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
98% confidence
Finding
The skill advertises a full patent FTO workflow with PatSnap, sequence alignment, structure search, claim analysis, and HTML report generation, but the finding indicates those capabilities are not actually implemented. In a legal-risk domain like patent clearance, this can mislead users into relying on incomplete or nonexistent analysis, creating significant business and legal exposure through false assurance.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The protocol is written to force a Chinese-language intake flow and does not offer the user any language-choice fallback. In a regulated legal-intelligence workflow like FTO analysis, this can cause users to misunderstand required inputs, jurisdiction filters, or legal-status options, which may lead to incomplete or incorrect analysis outputs. The issue is more significant here because the skill is used for patent-risk assessment across multiple jurisdictions, where precision in user instructions matters.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.