ClawHub
Back to skill

Security audit

Feature Spec Enhanced

Security checks across malware telemetry and agentic risk

Overview

This is a documentation helper that only guides PRD and HTML explainer writing; its main caveat is a Chinese-language HTML default.

Installers should know this skill may produce Chinese-language HTML explainer sections by default; request a different language explicitly if needed. I found no artifact-backed evidence of credential access, command execution, network calls, persistence, or destructive behavior.

SkillSpector

By NVIDIA
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

Medium
Confidence
95% confidence
Finding
The skill hard-codes Chinese locale and Chinese-language HTML output as the default/required format ('zh-CN' and Chinese text) without checking the user's requested language or locale. This can override user intent, cause misleading or unusable outputs for non-Chinese-speaking users, and in agent pipelines may lead to downstream rendering, review, or compliance issues when language/locale must match user or system expectations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.