ClawHub
Back to skill

Security audit

intimate-ch13-dissolution

Security checks across malware telemetry and agentic risk

Overview

This is a narrow Chinese-language study aid for a relationship textbook chapter, with no code execution, credential access, network use, or persistence.

Installers should treat this as a low-footprint educational skill. Be aware it will tend to answer in Chinese and discusses sensitive relationship topics; its content should not be treated as legal, clinical, emergency, or personal safety advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
92% confidence
Finding
The skill explicitly instructs the agent to answer in Chinese regardless of the user's language preference. This can override user choice or platform defaults, creating a prompt-level policy conflict and potentially degrading usability, accessibility, or accurate consent to communication preferences. In this educational context the risk is limited because it does not enable code execution, data exfiltration, or unsafe tool use.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.