ClawHub
Back to skill

Security audit

Brand Language Codifier

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped brand-language workflow that reads brand materials and project memory, then stages voice and naming guidance through disclosed registry proposal paths.

Before installing, confirm you are comfortable with the skill reading existing narrative or claims memory and optionally scraping public brand pages. Its persistence is limited to project memory drafts and registry proposal events for brand voice, naming, and claim follow-up.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.