ClawHub
Back to skill

Security audit

Change and Constants Framework

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only strategy coaching skill with no code execution, credential access, persistence, or data exfiltration behavior.

Installers should treat this as a strategy facilitation aid. The main practical consideration is whether users are comfortable with the Chinese framework labels appearing in outputs; no sensitive access or automatic actions are requested by the artifact.

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
Findings (1)

Natural-Language Policy Violations

Low
Confidence
96% confidence
Finding
The overview introduces core framework labels as Chinese-only terms (变 and 不变) within the primary instruction text. Because the file does not indicate that the skill is region-specific or offer the user an opt-in language choice, this can violate the policy against forcing a specific language or locale without user consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.