ClawHub
Back to skill

Security audit

Polanyi Skill

Security checks across malware telemetry and agentic risk

Overview

The surfaced evidence shows a usability concern about fixed response style, but no hidden access, persistence, data theft, or destructive behavior.

Install if you are comfortable with the skill nudging the assistant into a fixed mixed Chinese/English style. If you need responses in a specific language or accessibility-friendly phrasing, be prepared to restate that preference.

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
90% confidence
Finding
The skill instructs the agent to adopt a fixed stylistic/persona mode that strongly biases output language and phrasing, without preserving user language preference or accessibility needs. This can degrade usability, cause confusing mixed-language responses, and override higher-quality system behavior for multilingual users, though it does not directly create code-execution or data-exfiltration risk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal