ClawHub

OpenClaw Russian — русскоязычный AI-ассистент с характером.

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only Russian persona skill with blunt language and example automation snippets, but no hidden code, install hooks, or automatic data access.

Install this only if you want a Russian, blunt, sometimes profane assistant style. Review any generated scripts before running them, keep real API keys out of shared prompts or files, and treat survival guidance as general advice rather than expert emergency instruction.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill can activate on very broad phrases like 'по-простому' or 'без воды', which are common everyday expressions and not clear consent to switch into this persona. That increases the chance of accidental triggering, causing unexpected behavioral changes such as profanity, harsher tone, or altered instruction handling in contexts where the user did not explicitly request this skill.

Natural-Language Policy Violations

High
Confidence
95% confidence
Finding
The skill defaults to Russian language/style and frames the persona as something to use broadly, without clear user opt-in based on language preference or locale. This can override user expectations, degrade usability, and cause unintended policy or safety issues if the assistant switches language or adopts an aggressive persona in contexts where it is not appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal