ClawHub
Back to skill

Security audit

CB Brand Naming Trademark Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a descriptive brand-naming guide with clear legal-availability disclaimers, though some examples overstate what trademark and domain checks can prove.

Use this skill for structured brainstorming and preparation, not as proof that a name is legally available or that a domain or handle can be acquired. Treat any trademark, domain, social-handle, SEO, or cultural-risk output as preliminary unless you provide dated results from authoritative tools, and get qualified local trademark review before launch.

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 (4)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill metadata promises preliminary trademark and domain availability screening, while the README states the skill only returns evaluation frameworks and explicitly does not perform trademark search or legal clearance. This mismatch can mislead users into overtrusting the output and making branding decisions without actual legal or availability checks, creating legal, financial, and operational risk.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill’s examples and expected outputs repeatedly imply live trademark, domain, social-handle, and SEO availability checks, while the boundary and safety sections explicitly say such checks must not be presented as live facts without user-supplied authoritative data. This inconsistency can cause the agent to fabricate or overstate legal/commercial availability, creating misleading outputs that users may rely on for business decisions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The example response at L097 is entirely in Chinese and presents that behavior as the expected output for that scenario. This can be read as a locale-specific response policy without an explicit statement that the user may choose their preferred output language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest sets the skill language to "en", which imposes a specific language/locale in the configuration. There is no nearby indication that users can opt into another language or that the English-only constraint is required for a documented regional or compliance reason.

Content

No source excerpt is available for this finding.