ClawHub
Back to skill

Security audit

Ru Text

Security checks across malware telemetry and agentic risk

Overview

This is a Russian text-quality skill that changes writing style and typography, with no evidence of code execution, data access, persistence, or malicious behavior.

Install this if you want Russian text automatically normalized for typography and editorial style. Avoid or disable it for tasks that require exact reproduction of Russian text, legal wording, code-adjacent strings, test fixtures, or quoted material where character-level fidelity matters.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill is configured with `always: true` and a broad description that includes automatic activation on Russian text output, which can trigger it in many contexts without clear user intent. This creates a policy/control risk: the skill may unexpectedly modify outputs or influence tasks outside narrow proofreading/editing scenarios.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The skill states that typography rules apply to all Russian text output without exception, which overrides user autonomy and can cause unintended transformation of content. In security-sensitive or fidelity-sensitive contexts, forced rewriting may alter quoted material, code-adjacent text, legal wording, or exact user-provided strings.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.