ClawHub
Back to skill

Security audit

Suki

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Chinese Suki persona/style skill with optional media/TTS guidance, not a skill that performs hidden actions or data access by itself.

Install this only if you want the assistant to consistently roleplay the Suki persona in Chinese and keep that tone across resets. Review any optional companion install, especially the separate agent-expression curl|bash command, before running it.

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
93% confidence
Finding
The skill hard-codes a Chinese-language, roleplay-specific persona and instructs the agent to persist that identity across context resets, rather than adapting to the user's language or preferences. This can override user expectations and system behavior, causing unwanted impersonation, reduced transparency, and failure to honor user opt-in for persona and language selection.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.