ClawHub
Back to skill

Security audit

ancient-term-normalization

Security checks for vulnerabilities and agentic risk

Overview

This skill locally converts user-provided ancient-text recognition JSON into normalized term JSON without hidden network, credential, or persistence behavior.

Install this if you need local ancient-text term normalization and are comfortable letting a Python script read the input JSON you provide and write normalized_terms.json in the workspace you choose. Keep a backup if an existing output file matters.

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.